Search

The article discusses the use of Artificial Intelligence (A.I.) tools, specifically chatbots, in second language acquisition. It highlights the potential benefits and concerns associated with the use of A.I. in language learning. The article calls for systematic research to explore the capabilities of A.I. language models, such as ChatGPT, and their impact on language learning. It suggests three strands of research: examining the language model itself, investigating learner interactions with the model, and exploring the effects of the model on learners. The article emphasizes the need to connect this research with existing studies in Instructed Second Language Acquisition (ISLA) to enhance our understanding of language learning conditions. [Extracted from the article]

Purpose: This paper aims to explore ChatGPT's (generative pre-trained transformers) potential as a tool for retailers to improve customer experience and boost sales. While it provides benefits like personalized recommendations and 24/7 assistance, there are limitations, like difficulty in understanding unconventional language. The paper stresses careful integration to overcome these limitations and create a better customer experience. Additionally, it discusses the potential for further development and integration of ChatGPT in retail, such as generating product descriptions and virtual try-on experiences. Finally, the paper encourages retailers to embrace ChatGPT to meet their customer needs. Design/methodology/approach: Case-based methodology involves using specific cases or examples to explore a broader issue or phenomenon. Researchers have analysed real-world cases to identify patterns, themes and insights that can be applied to other contexts or situations. This was useful for understanding complex and multifaceted issues as it allowed us to delve deeper into specific examples and explore the nuances of the situation. Findings: While ChatGPT is a powerful tool for retailers, limitations such as difficulty in understanding non-standard accents and unconventional language can arise, causing customer frustration. Retail managers must integrate ChatGPT in a way that enhances customer experience. In the future, ChatGPT has the potential to generate product descriptions, provide virtual try-on experiences and integrate with augmented or virtual reality technology to offer more immersive experiences. Careful consideration and integration can help retailers overcome these limitations and offer personalized recommendations, round-the-clock assistance and an engaging customer experience that improves sales. Originality/value: The case topic is very much in a novel stage of research and writing. [ABSTRACT FROM AUTHOR]

Large Language Models (LLMs), such as ChatGPT, encounter 'jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting jailbreak prompts that bypass LLM defenses. Our technique iteratively transforms harmful prompts into benign expressions directly utilizing the target LLM, predicated on the hypothesis that LLMs can autonomously generate expressions that evade safeguards. Through experiments conducted with ChatGPT (GPT-3.5 and GPT-4) and Gemini-Pro, our method consistently achieved an attack success rate exceeding 80% within an average of five iterations for forbidden questions and proved to be robust against model updates. The jailbreak prompts generated were not only naturally worded and succinct, but also challenging to defend against. These findings suggest that the creation of effective jailbreak prompts is less complex than previously believed, underscoring the heightened risk posed by black-box jailbreak attacks. [ABSTRACT FROM AUTHOR]

Since the AI 'architectural explosion' of 2022, and as things have become clearer but have not yet settled down, a whole raft of possibilities for creativity and commercial exploration are emerging. Architectural and urban designer Wanyu He explains some of these opportunities, and also reminds us of the ethical and societal concerns about this technology – its biases and blindnesses – which must be addressed before these new approaches can be applied equitably. [ABSTRACT FROM AUTHOR]

This article explores the impact of cable news, specifically Fox News and MSNBC, on viewers' policy views in the United States. The authors analyze the coverage of four policy issues and link it to viewership of these channels. They find that viewers tend to align with the slant of coverage and that this has a significant influence on their policy views, even after accounting for individual ideology and party affiliation. The study contributes to existing research on the political effects of mass media, emphasizing the need to understand the role of media in shaping public opinion. [Extracted from the article]

Automated stance detection and related machine learning methods can provide useful insights for media monitoring and academic research. Many of these approaches require annotated training datasets, which limits their applicability for languages where these may not be readily available. This paper explores the applicability of large language models for automated stance detection in a challenging scenario, involving a morphologically complex, lower-resource language, and a socio-culturally complex topic, immigration. If the approach works in this case, it can be expected to perform as well or better in less demanding scenarios. We annotate a large set of pro- and anti-immigration examples to train and compare the performance of multiple language models. We also probe the usability of GPT-3.5 (that powers ChatGPT) as an instructable zero-shot classifier for the same task. The supervised models achieve acceptable performance, but GPT-3.5 yields similar accuracy. As the latter does not require tuning with annotated data, it constitutes a potentially simpler and cheaper alternative for text classification tasks, including in lower-resource languages. We further use the best-performing supervised model to investigate diachronic trends over seven years in two corpora of Estonian mainstream and right-wing populist news sources, demonstrating the applicability of automated stance detection for news analytics and media monitoring settings even in lower-resource scenarios, and discuss correspondences between stance changes and real-world events. [ABSTRACT FROM AUTHOR]

While there is data assessing the test performance of artificial intelligence (AI) chatbots, including the Generative Pre-trained Transformer 4.0 (GPT 4) chatbot (ChatGPT 4.0), there is scarce data on its diagnostic accuracy of clinical cases. We assessed the large language model (LLM), ChatGPT 4.0, on its ability to answer questions from the United States Medical Licensing Exam (USMLE) Step 2, as well as its ability to generate a differential diagnosis based on corresponding clinical vignettes from published case reports. A total of 109 Step 2 Clinical Knowledge (CK) practice questions were inputted into both ChatGPT 3.5 and ChatGPT 4.0, asking ChatGPT to pick the correct answer. Compared to its previous version, ChatGPT 3.5, we found improved accuracy of ChatGPT 4.0 when answering these questions, from 47.7 to 87.2% (p = 0.035) respectively. Utilizing the topics tested on Step 2 CK questions, we additionally found 63 corresponding published case report vignettes and asked ChatGPT 4.0 to come up with its top three differential diagnosis. ChatGPT 4.0 accurately created a shortlist of differential diagnoses in 74.6% of the 63 case reports (74.6%). We analyzed ChatGPT 4.0's confidence in its diagnosis by asking it to rank its top three differentials from most to least likely. Out of the 47 correct diagnoses, 33 were the first (70.2%) on the differential diagnosis list, 11 were second (23.4%), and three were third (6.4%). Our study shows the continued iterative improvement in ChatGPT's ability to answer standardized USMLE questions accurately and provides insights into ChatGPT's clinical diagnostic accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we experimentally evaluate the zero-shot performance of GPT-4 against prior generations of GPT on the entire uniform bar examination (UBE), including not only the multiple-choice multistate bar examination (MBE), but also the open-ended multistate essay exam (MEE) and multistate performance test (MPT) components. On the MBE, GPT-4 significantly outperforms both human test-takers and prior models, demonstrating a 26% increase over ChatGPT and beating humans in five of seven subject areas. On the MEE and MPT, which have not previously been evaluated by scholars, GPT-4 scores an average of 4.2/6.0 when compared with much lower scores for ChatGPT. Graded across the UBE components, in the manner in which a human test-taker would be, GPT-4 scores approximately 297 points, significantly in excess of the passing threshold for all UBE jurisdictions. These findings document not just the rapid and remarkable advance of large language model performance generally, but also the potential for such models to support the delivery of legal services in society. This article is part of the theme issue 'A complexity science approach to law and governance'. [ABSTRACT FROM AUTHOR]

Better understanding of Large Language Models' (LLMs) legal analysis abilities can contribute to improving the efficiency of legal services, governing artificial intelligence and leveraging LLMs to identify inconsistencies in law. This paper explores LLM capabilities in applying tax law. We choose this area of law because it has a structure that allows us to set up automated validation pipelines across thousands of examples, requires logical reasoning and maths skills, and enables us to test LLM capabilities in a manner relevant to real-world economic lives of citizens and companies. Our experiments demonstrate emerging legal understanding capabilities, with improved performance in each subsequent OpenAI model release. We experiment with retrieving and using the relevant legal authority to assess the impact of providing additional legal context to LLMs. Few-shot prompting, presenting examples of question–answer pairs, is also found to significantly enhance the performance of the most advanced model, GPT-4. The findings indicate that LLMs, particularly when combined with prompting enhancements and the correct legal texts, can perform at high levels of accuracy but not yet at expert tax lawyer levels. As LLMs continue to advance, their ability to reason about law autonomously could have significant implications for the legal profession and AI governance. This article is part of the theme issue 'A complexity science approach to law and governance'. [ABSTRACT FROM AUTHOR]

Identification of druggable proteins can greatly reduce the cost of discovering new potential drugs. Traditional experimental approaches to exploring these proteins are often costly, slow, and labor-intensive, making them impractical for large-scale research. In response, recent decades have seen a rise in computational methods. These alternatives support drug discovery by creating advanced predictive models. In this study, we proposed a fast and precise classifier for the identification of druggable proteins using a protein language model (PLM) with fine-tuned evolutionary scale modeling 2 (ESM-2) embeddings, achieving 95.11% accuracy on the benchmark dataset. Furthermore, we made a careful comparison to examine the predictive abilities of ESM-2 embeddings and position-specific scoring matrix (PSSM) features by using the same classifiers. The results suggest that ESM-2 embeddings outperformed PSSM features in terms of accuracy and efficiency. Recognizing the potential of language models, we also developed an end-to-end model based on the generative pre-trained transformers 2 (GPT-2) with modifications. To our knowledge, this is the first time a large language model (LLM) GPT-2 has been deployed for the recognition of druggable proteins. Additionally, a more up-to-date dataset, known as Pharos, was adopted to further validate the performance of the proposed model. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) find increasing applications in many fields. Here, three LLM chatbots (ChatGPT-3.5, ChatGPT-4, and Bard) are assessed in their current form, as publicly available, for their ability to recognize Alzheimer's dementia (AD) and Cognitively Normal (CN) individuals using textual input derived from spontaneous speech recordings. A zero-shot learning approach is used at two levels of independent queries, with the second query (chain-of-thought prompting) eliciting more detailed information than the first. Each LLM chatbot's performance is evaluated on the prediction generated in terms of accuracy, sensitivity, specificity, precision, and F1 score. LLM chatbots generated a three-class outcome ("AD", "CN", or "Unsure"). When positively identifying AD, Bard produced the highest true-positives (89% recall) and highest F1 score (71%), but tended to misidentify CN as AD, with high confidence (low "Unsure" rates); for positively identifying CN, GPT-4 resulted in the highest true-negatives at 56% and highest F1 score (62%), adopting a diplomatic stance (moderate "Unsure" rates). Overall, the three LLM chatbots can identify AD vs. CN, surpassing chance-levels, but do not currently satisfy the requirements for clinical application. [ABSTRACT FROM AUTHOR]

Business Process Model and Notation (BPMN) is a standard for formally modeling complex business processes. Manual creation of BPMN models can be time-consuming and error-prone, prompting a need for automation. Existing approaches, such as rule-based methods, machine learning, and machine translation, have progressed but face accuracy and real-world applicability challenges. In this research paper, we propose a novel method for automated extraction of BPMN models from textual descriptions using natural language processing (NLP) tools and deep learning models, including the spaCy library for text processing, a fine-tuned BERT model, and state-of-the-art large language models like GPT-3.5-Turbo and GPT-4. We utilize Graphviz, an open-source graph visualization software, to visualize the extracted processes. Our method supports representing tasks, exclusive gateways, parallel gateways, and start and end events in the generated BPMN models. The evaluation of 31 textual descriptions shows that our method generates process models with 96% accuracy using GPT-4 and 80% accuracy using GPT-3.5-Turbo large language models. Although subject to certain limitations, such as occasional inaccuracies in model outputs and reliance on well-formed input text, our approach offers a valuable contribution to the growing body of research on automating BPMN model generation. [ABSTRACT FROM AUTHOR]

In the realm of pretrained language models (PLMs), the exponential increase in computational resources and time required for training as model sizes expand presents a significant challenge. This paper proposes an innovative approach named neighbor attention initialization (NAI) to expedite the training process of larger PLMs by leveraging smaller PLMs through parameter initialization. Our methodology hinges on the hypothesis that smaller PLMs, having already learned fundamental language structures and patterns, can provide a robust foundational knowledge base for larger models, which is called function preserving. Specifically, we present a comprehensive framework detailing the process of transferring learned features on transformer-based language models mainly using the neighbor attention head and neighbor layer. We conducted experiments in GPT-2 and demonstrated that our method yields considerable savings in training costs compared to standard approaches, including learning from scratch and bert2BERT, indicating a notable improvement in training efficiency for large PLMs. [ABSTRACT FROM AUTHOR]

This study investigates the strategic decision-making abilities of large language models (LLMs) via the game of Tic-Tac-Toe, renowned for its straightforward rules and definitive outcomes. We developed a mobile application coupled with web services, facilitating gameplay among leading LLMs, including Jurassic-2 Ultra by AI21, Claude 2.1 by Anthropic, Gemini-Pro by Google, GPT-3.5-Turbo and GPT-4 by OpenAI, Llama2-70B by Meta, and Mistral Large by Mistral, to assess their rule comprehension and strategic thinking. Using a consistent prompt structure in 10 sessions for each LLM pair, we systematically collected data on wins, draws, and invalid moves across 980 games, employing two distinct prompt types to vary the presentation of the game's status. Our findings reveal significant performance variations among the LLMs. Notably, GPT-4, GPT-3.5-Turbo, and Llama2 secured the most wins with the list prompt, while GPT-4, Gemini-Pro, and Mistral Large excelled using the illustration prompt. GPT-4 emerged as the top performer, achieving victory with the minimum number of moves and the fewest errors for both prompt types. This research introduces a novel methodology for assessing LLM capabilities using a game that can illuminate their strategic thinking abilities. Beyond enhancing our comprehension of LLM performance, this study lays the groundwork for future exploration into their utility in complex decision-making scenarios, offering directions for further inquiry and the exploration of LLM limits within game-based frameworks. [ABSTRACT FROM AUTHOR]

In this study, we conduct a pioneering and comprehensive examination of ChatGPT's (GPT-3.5 Turbo) capabilities within the realm of Korean Grammatical Error Correction (K-GEC). Given the Korean language's agglutinative nature and its rich linguistic intricacies, the task of accurately correcting errors while preserving Korean-specific sentiments is notably challenging. Utilizing a systematic categorization of Korean grammatical errors, we delve into a meticulous, case-specific analysis to identify the strengths and limitations of a ChatGPT-based correction system. We also critically assess influential parameters like temperature and specific error criteria, illuminating potential strategies to enhance ChatGPT's efficacy in K-GEC tasks. Our findings offer valuable contributions to the expanding domain of NLP research centered on the Korean language. [ABSTRACT FROM AUTHOR]

Health equity and accessing Spanish kidney transplant information continues being a substantial challenge facing the Hispanic community. This study evaluated ChatGPT's capabilities in translating 54 English kidney transplant frequently asked questions (FAQs) into Spanish using two versions of the AI model, GPT-3.5 and GPT-4.0. The FAQs included 19 from Organ Procurement and Transplantation Network (OPTN), 15 from National Health Service (NHS), and 20 from National Kidney Foundation (NKF). Two native Spanish-speaking nephrologists, both of whom are of Mexican heritage, scored the translations for linguistic accuracy and cultural sensitivity tailored to Hispanics using a 1–5 rubric. The inter-rater reliability of the evaluators, measured by Cohen's Kappa, was 0.85. Overall linguistic accuracy was 4.89 ± 0.31 for GPT-3.5 versus 4.94 ± 0.23 for GPT-4.0 (non-significant p = 0.23). Both versions scored 4.96 ± 0.19 in cultural sensitivity (p = 1.00). By source, GPT-3.5 linguistic accuracy was 4.84 ± 0.37 (OPTN), 4.93 ± 0.26 (NHS), 4.90 ± 0.31 (NKF). GPT-4.0 scored 4.95 ± 0.23 (OPTN), 4.93 ± 0.26 (NHS), 4.95 ± 0.22 (NKF). For cultural sensitivity, GPT-3.5 scored 4.95 ± 0.23 (OPTN), 4.93 ± 0.26 (NHS), 5.00 ± 0.00 (NKF), while GPT-4.0 scored 5.00 ± 0.00 (OPTN), 5.00 ± 0.00 (NHS), 4.90 ± 0.31 (NKF). These high linguistic and cultural sensitivity scores demonstrate Chat GPT effectively translated the English FAQs into Spanish across systems. The findings suggest Chat GPT's potential to promote health equity by improving Spanish access to essential kidney transplant information. Additional research should evaluate its medical translation capabilities across diverse contexts/languages. These English-to-Spanish translations may increase access to vital transplant information for underserved Spanish-speaking Hispanic patients. [ABSTRACT FROM AUTHOR]

The article discusses the documented inequalities in health status and healthcare provision for LGBTQIA+ individuals, specifically focusing on cardiovascular health. These disparities vary based on sexual orientation, gender identity, race, disability, and socioeconomic status. Despite legislation prohibiting discrimination, LGBTQIA+ people continue to face barriers in accessing culturally competent healthcare across the European Union and elsewhere. The article emphasizes the need for urgent action from cardiovascular professionals to address these inequalities and provides resources and areas of focus for research and clinical practice. [Extracted from the article]

Artificial Intelligence (AI) has emerged as a transformative tool in various fields, including medicinal chemistry and drug discovery. The integration of artificial intelligence (AI) and machine learning (ML) technologies in medicinal chemistry has revolutionized drug discovery processes. Among AI models, ChatGPT (Generative Pre‐trained Transformer) has shown remarkable capabilities in natural language understanding and generation. This review article delves into the potential applications and prospects of ChatGPT in the domain of medicinal chemistry, focusing on its contributions to drug discovery, compound design, virtual screening, target identification, and optimization of pharmacokinetic properties. ChatGPT′s ability to generate contextually relevant text makes it a valuable tool for data mining and analysis of vast chemical and biological information repositories. In this review article, the authors have discussed the challenges and ethical considerations associated with the implementation of ChatGPT 3.5 in medicinal chemistry research. Authors also extend their acknowledgment to ChatGPT (version 3.5) for its contribution in furnishing responses to the prompt, thereby shedding light on the applications of ChatGPT in the field of medicinal chemistry. The authors have analyzed the responses of ChatGPT. [ABSTRACT FROM AUTHOR]

Motivation Large Language Models (LLMs) have the potential to revolutionize the field of Natural Language Processing, excelling not only in text generation and reasoning tasks but also in their ability for zero/few-shot learning, swiftly adapting to new tasks with minimal fine-tuning. LLMs have also demonstrated great promise in biomedical and healthcare applications. However, when it comes to Named Entity Recognition (NER), particularly within the biomedical domain, LLMs fall short of the effectiveness exhibited by fine-tuned domain-specific models. One key reason is that NER is typically conceptualized as a sequence labeling task, whereas LLMs are optimized for text generation and reasoning tasks. Results We developed an instruction-based learning paradigm that transforms biomedical NER from a sequence labeling task into a generation task. This paradigm is end-to-end and streamlines the training and evaluation process by automatically repurposing pre-existing biomedical NER datasets. We further developed BioNER-LLaMA using the proposed paradigm with LLaMA-7B as the foundational LLM. We conducted extensive testing on BioNER-LLaMA across three widely recognized biomedical NER datasets, consisting of entities related to diseases, chemicals, and genes. The results revealed that BioNER-LLaMA consistently achieved higher F1-scores ranging from 5% to 30% compared to the few-shot learning capabilities of GPT-4 on datasets with different biomedical entities. We show that a general-domain LLM can match the performance of rigorously fine-tuned PubMedBERT models and PMC-LLaMA, biomedical-specific language model. Our findings underscore the potential of our proposed paradigm in developing general-domain LLMs that can rival SOTA performances in multi-task, multi-domain scenarios in biomedical and health applications. Availability and implementation Datasets and other resources are available at https://github.com/BIDS-Xu-Lab/BioNER-LLaMA. [ABSTRACT FROM AUTHOR]

This study explored the application of generative pre-trained transformer (GPT) agents based on medical guidelines using large language model (LLM) technology for traumatic brain injury (TBI) rehabilitation-related questions. To assess the effectiveness of multiple agents (GPT-agents) created using GPT-4, a comparison was conducted using direct GPT-4 as the control group (GPT-4). The GPT-agents comprised multiple agents with distinct functions, including "Medical Guideline Classification", "Question Retrieval", "Matching Evaluation", "Intelligent Question Answering (QA)", and "Results Evaluation and Source Citation". Brain rehabilitation questions were selected from the doctor-patient Q&A database for assessment. The primary endpoint was a better answer. The secondary endpoints were accuracy, completeness, explainability, and empathy. Thirty questions were answered; overall GPT-agents took substantially longer and more words to respond than GPT-4 (time: 54.05 vs. 9.66 s, words: 371 vs. 57). However, GPT-agents provided superior answers in more cases compared to GPT-4 (66.7 vs. 33.3%). GPT-Agents surpassed GPT-4 in accuracy evaluation (3.8 ± 1.02 vs. 3.2 ± 0.96, p = 0.0234). No difference in incomplete answers was found (2 ± 0.87 vs. 1.7 ± 0.79, p = 0.213). However, in terms of explainability (2.79 ± 0.45 vs. 07 ± 0.52, p < 0.001) and empathy (2.63 ± 0.57 vs. 1.08 ± 0.51, p < 0.001) evaluation, the GPT-agents performed notably better. Based on medical guidelines, GPT-agents enhanced the accuracy and empathy of responses to TBI rehabilitation questions. This study provides guideline references and demonstrates improved clinical explainability. However, further validation through multicenter trials in a clinical setting is necessary. This study offers practical insights and establishes groundwork for the potential theoretical integration of LLM-agents medicine. [ABSTRACT FROM AUTHOR]

Can large language models produce expert‐quality philosophical texts? To investigate this, we fine‐tuned GPT‐3 with the works of philosopher Daniel Dennett. To evaluate the model, we asked the real Dennett 10 philosophical questions and then posed the same questions to the language model, collecting four responses for each question without cherry‐picking. Experts on Dennett's work succeeded at distinguishing the Dennett‐generated and machine‐generated answers above chance but substantially short of our expectations. Philosophy blog readers performed similarly to the experts, while ordinary research participants were near chance distinguishing GPT‐3's responses from those of an "actual human philosopher". [ABSTRACT FROM AUTHOR]

Summary: In a first‐of‐its‐kind study, we assessed the capabilities of large language models (LLMs) in making complex decisions in haematopoietic stem cell transplantation. The evaluation was conducted not only for Generative Pre‐trained Transformer 4 (GPT‐4) but also conducted on other artificial intelligence models: PaLm 2 and Llama‐2. Using detailed haematological histories that include both clinical, molecular and donor data, we conducted a triple‐blind survey to compare LLMs to haematology residents. We found that residents significantly outperformed LLMs (p = 0.02), particularly in transplant eligibility assessment (p = 0.01). Our triple‐blind methodology aimed to mitigate potential biases in evaluating LLMs and revealed both their promise and limitations in deciphering complex haematological clinical scenarios. [ABSTRACT FROM AUTHOR]

In late 2023, the image-reading capability added to a Generative Pre-trained Transformer (GPT) framework provided the opportunity to potentially revolutionize the way we view and understand geographic maps, the core component of cartography, geography, and spatial data science. In this study, we explore reading and analyzing maps with the latest version of GPT-4-vision-preview (GPT-4V), to fully evaluate its advantages and disadvantages in comparison with human eye-based visual inspections. We found that GPT-4V is able to properly retrieve information from various types of maps in different scales and spatiotemporal resolutions. GPT-4V can also perform basic map analysis, such as identifying visual changes before and after a natural disaster. It has the potential to replace human efforts by examining batches of maps, accurately extracting information from maps, and linking observed patterns with its pre-trained large dataset. However, it is encumbered by limitations such as diminished accuracy in visual content extraction and a lack of validation. This paper sets an example of effectively using GPT-4V for map reading and analytical tasks, which is a promising application for large multimodal models, large language models, and artificial intelligence. [ABSTRACT FROM AUTHOR]

Recent advances in knowledge graphs show great promise to link various data together to provide a semantic network. Place is an important part in the big picture of the knowledge graph since it serves as a powerful glue to link any data to its georeference. A key technical challenge in constructing knowledge graphs with location nodes as geographical references is the matching of place entities. Traditional methods typically rely on rule-based matching or machine-learning techniques to determine if two place names refer to the same location. However, these approaches are often limited in the feature selection of places for matching criteria, resulting in imbalanced consideration of spatial and semantic features. Deep feature-based methods such as deep learning methods show great promise for improved place data conflation. This paper introduces a Semantic-Spatial Aware Representation Learning Model (SSARLM) for Place Matching. SSARLM liberates the tedious manual feature extraction step inherent in traditional methods, enabling an end-to-end place entity matching pipeline. Furthermore, we introduce an embedding fusion module designed for the unified encoding of semantic and spatial information. In the experiment, we evaluate the approach to named places from Guangzhou and Shanghai cities in GeoNames, OpenStreetMap (OSM), and Baidu Map. The SSARLM is compared with several classical and commonly used binary classification machine learning models, and the state-of-the-art large language model, GPT-4. The results demonstrate the benefit of pre-trained models in data conflation of named places. [ABSTRACT FROM AUTHOR]

Background and purpose: The integration of artificial intelligence (AI) in healthcare has the potential to revolutionize patient care and clinical decision‐making. This study aimed to explore the reliability of large language models in neurology by comparing the performance of an AI chatbot with neurologists in diagnostic accuracy and decision‐making. Methods: A cross‐sectional observational study was conducted. A pool of clinical cases from the American Academy of Neurology's Question of the Day application was used as the basis for the study. The AI chatbot used was ChatGPT, based on GPT‐3.5. The results were then compared to neurology peers who also answered the questions—a mean of 1500 neurologists/neurology residents. Results: The study included 188 questions across 22 different categories. The AI chatbot demonstrated a mean success rate of 71.3% in providing correct answers, with varying levels of proficiency across different neurology categories. Compared to neurology peers, the AI chatbot performed at a similar level, with a mean success rate of 69.2% amongst peers. Additionally, the AI chatbot achieved a correct diagnosis in 85.0% of cases and it provided an adequate justification for its correct responses in 96.1%. Conclusions: The study highlights the potential of AI, particularly large language models, in assisting with clinical reasoning and decision‐making in neurology and emphasizes the importance of AI as a complementary tool to human expertise. Future advancements and refinements are needed to enhance the AI chatbot's performance and broaden its application across various medical specialties. [ABSTRACT FROM AUTHOR]

In the review by Omiye and colleagues ([1]), the authors identified several numerical input errors in Figure 2. The following corrections have been made to address these: Vicuna was changed from 7B to 13B. ChatGPT was renamed as GPT-3. Med-PALM was changed from 540B+ to 540B. BioGPT was changed from 357B to 347M. PMC-LLaMA was changed from 75B to 13B. BioGPT-Large was added.These changes do not affect the conclusions of the article. [Extracted from the article]

This research breaks new ground by utilizing the advanced natural language processing (NLP) capabilities of OpenAI's GPT-3.5 Turbo model for the extraction of voice of customer (VoC) data from online customer support interactions on Twitter. Traditional methods of VoC extraction have typically fallen short in capturing the richness and nuance of customer sentiment. Contemporary machine learning (ML) approaches, while improved, still struggle to interpret the contextual subtleties of digital customer communications effectively. This study showcases the innovative deployment of GPT-3.5 Turbo, demonstrating its superior performance in extracting VoC through a deeper understanding of conversational context and a more intuitive, chat-based data processing. Furthermore, the large-scale, multilingual processing capabilities of this model offer a more comprehensive and inclusive analysis of VoC. The study ties these advancements to Lean Six Sigma 4.0, illustrating how the integration of GPT-3.5 Turbo's transformative capabilities can elevate the customer-centric approach of Lean Six Sigma in the era of Industry 4.0. This innovative exploration points to a significant evolution in VoC analysis, offering potential for more insightful, real-time data–driven customer service strategies and a more substantial foundation for decision-making in product development and process improvement. Future research is encouraged to validate these preliminary findings and to investigate ethical considerations associated with the use of such advanced NLP models. [ABSTRACT FROM AUTHOR]

Purpose: Confocal Laser Endomicroscopy (CLE) is an imaging tool, that has demonstrated potential for intraoperative, real-time, non-invasive, microscopical assessment of surgical margins of oropharyngeal squamous cell carcinoma (OPSCC). However, interpreting CLE images remains challenging. This study investigates the application of OpenAI's Generative Pretrained Transformer (GPT) 4.0 with Vision capabilities for automated classification of CLE images in OPSCC. Methods: CLE Images of histological confirmed SCC or healthy mucosa from a database of 12 809 CLE images from 5 patients with OPSCC were retrieved and anonymized. Using a training data set of 16 images, a validation set of 139 images, comprising SCC (83 images, 59.7%) and healthy normal mucosa (56 images, 40.3%) was classified using the application programming interface (API) of GPT4.0. The same set of images was also classified by CLE experts (two surgeons and one pathologist), who were blinded to the histology. Diagnostic metrics, the reliability of GPT and inter-rater reliability were assessed. Results: Overall accuracy of the GPT model was 71.2%, the intra-rater agreement was κ = 0.837, indicating an almost perfect agreement across the three runs of GPT-generated results. Human experts achieved an accuracy of 88.5% with a substantial level of agreement (κ = 0.773). Conclusions: Though limited to a specific clinical framework, patient and image set, this study sheds light on some previously unexplored diagnostic capabilities of large language models using few-shot prompting. It suggests the model's ability to extrapolate information and classify CLE images with minimal example data. Whether future versions of the model can achieve clinically relevant diagnostic accuracy, especially in uncurated data sets, remains to be investigated. [ABSTRACT FROM AUTHOR]

Introduction: Biologic therapies for Chronic Rhinosinusitis with Nasal Polyps (CRSwNP) have emerged as an auspicious treatment alternative. However, the ideal patient population, dosage, and treatment duration are yet to be well-defined. Moreover, biologic therapy has disadvantages, such as high costs and limited access. The proposal of a novel Artificial Intelligence (AI) algorithm offers an intriguing solution for optimizing decision-making protocols. Methods: The AI algorithm was initially programmed to conduct a systematic literature review searching for the current primary guidelines on biologics' clinical efficacy and safety in treating CRSwNP. The review included a total of 12 studies: 6 systematic reviews, 4 expert consensus guidelines, and 2 surveys. Simultaneously, two independent human researchers conducted a literature search to compare the results. Subsequently, the AI was tasked to critically analyze the identified papers, highlighting strengths and weaknesses, thereby creating a decision-making algorithm and pyramid flow chart. Results: The studies evaluated various biologics, including monoclonal antibodies targeting Interleukin-5 (IL-5), IL-4, IL-13, and Immunoglobulin E (IgE), assessing their effectiveness in different patient populations, such as those with comorbid asthma or refractory CRSwNP. Dupilumab, a monoclonal antibody targeting the IL-4 receptor alpha subunit, demonstrated significant improvement in nasal symptoms and quality of life in patients with CRSwNP in several randomized controlled trials and systematic reviews. Similarly, mepolizumab and reslizumab, which target IL-5, have also shown efficacy in reducing nasal polyp burden and improving symptoms in patients with CRSwNP, particularly those with comorbid asthma. However, additional studies are required to confirm the long-term efficacy and safety of these biologics in treating CRSwNP. Conclusions: Biologic therapies have surfaced as a promising treatment option for patients with severe or refractory CRSwNP; however, the optimal patient population, dosage, and treatment duration are yet to be defined. The application of AI in decision-making protocols and the creation of therapeutic algorithms for biologic drug selection, could offer fascinating future prospects in the management of CRSwNP. [ABSTRACT FROM AUTHOR]

Introduction: Chatbot generative pre-trained transformer (ChatGPT) is a new artificial intelligence-powered language model of chatbot able to help otolaryngologists in practice and research. We investigated the accuracy of ChatGPT-3.5 and -4 in the referencing of manuscripts published in otolaryngology. Methods: ChatGPT-3.5 and ChatGPT-4 were interrogated for providing references of the top-30 most cited papers in otolaryngology in the past 40 years including clinical guidelines and key studies that changed the practice. The responses were regenerated three times to assess the accuracy and stability of ChatGPT. ChatGPT-3.5 and ChatGPT-4 were compared for accuracy of reference and potential mistakes. Results: The accuracy of ChatGPT-3.5 and ChatGPT-4.0 ranged from 47% to 60%, and 73% to 87%, respectively (p < 0.005). ChatGPT-3.5 provided 19 inaccurate references and invented 2 references throughout the regenerated questions. ChatGPT-4.0 provided 13 inaccurate references, while it proposed only one invented reference. The stability of responses throughout regenerated answers was mild (k = 0.238) and moderate (k = 0.408) for ChatGPT-3.5 and 4.0, respectively. Conclusions: ChatGPT-4.0 reported higher accuracy than the free-access version (3.5). False references were detected in both 3.5 and 4.0 versions. Practitioners need to be careful regarding the use of ChatGPT in the reach of some key reference when writing a report. [ABSTRACT FROM AUTHOR]

This study introduces Protectbot, an innovative chatbot framework designed to improve safety in children's online gaming environments. At its core, Protectbot incorporates DialoGPT, a conversational Artificial Intelligence (AI) model rooted in Generative Pre-trained Transformer 2 (GPT-2) technology, engineered to simulate human-like interactions within gaming chat rooms. The framework is distinguished by a robust text classification strategy, rigorously trained on the Publicly Available Natural 2012 (PAN12) dataset, aimed at identifying and mitigating potential sexual predatory behaviors through chat conversation analysis. By utilizing fastText for word embeddings to vectorize sentences, we have refined a support vector machine (SVM) classifier, achieving remarkable performance metrics, with recall, accuracy, and F-scores approaching 0.99. These metrics not only demonstrate the classifier's effectiveness, but also signify a significant advancement beyond existing methodologies in this field. The efficacy of our framework is additionally validated on a custom dataset, composed of 71 predatory chat logs from the Perverted Justice website, further establishing the reliability and robustness of our classifier. Protectbot represents a crucial innovation in enhancing child safety within online gaming communities, providing a proactive, AI-enhanced solution to detect and address predatory threats promptly. Our findings highlight the immense potential of AI-driven interventions to create safer digital spaces for young users. [ABSTRACT FROM AUTHOR]

Effectively understanding and categorizing vulnerabilities is vital in the ever-evolving cybersecurity landscape, since only one exposure can have a devastating effect on the entire system. Given the increasingly massive number of threats and the size of modern infrastructures, the need for structured, uniform cybersecurity knowledge systems arose. To tackle this challenge, the MITRE Corporation set up two powerful sources of cyber threat and vulnerability information, namely the Common Vulnerabilities and Exposures (CVEs) list focused on identifying and fixing software vulnerabilities, and the MITRE ATT&CK Enterprise Matrix, which is a framework for defining and categorizing adversary actions and ways to defend against them. At the moment, the two are not directly linked, even if such a link would have a significant positive impact on the cybersecurity community. This study aims to automatically map CVEs to the corresponding 14 MITRE ATT&CK tactics using state-of-the-art transformer-based models. Various architectures, from encoders to generative large-scale models, are employed to tackle this multilabel classification problem. Our results are promising, with a SecRoBERTa model performing best with an F1 score of 77.81%, which is closely followed by SecBERT (78.77%), CyBERT (78.54%), and TARS (78.01%), while GPT-4 showed a weak performance in zero-shot settings (22.04%). In addition, we perform an in-depth error analysis to better understand the models' performance and limitations. We release the code used for all experiments as open source. [ABSTRACT FROM AUTHOR]

Short texts generated by individuals in online environments can provide social and behavioral scientists with rich insights into these individuals' internal states. Trained manual coders can reliably interpret expressions of such internal states in text. However, manual coding imposes restrictions on the number of texts that can be analyzed, limiting our ability to extract insights from large-scale textual data. We evaluate the performance of several automatic text analysis methods in approximating trained human coders' evaluations across four coding tasks encompassing expressions of motives, norms, emotions, and stances. Our findings suggest that commonly used dictionaries, although performing well in identifying infrequent categories, generate false positives too frequently compared to other methods. We show that large language models trained on manually coded data yield the highest performance across all case studies. However, there are also instances where simpler methods show almost equal performance. Additionally, we evaluate the effectiveness of cutting-edge generative language models like GPT-4 in coding texts for internal states with the help of short instructions (so-called zero-shot classification). While promising, these models fall short of the performance of models trained on manually analyzed data. We discuss the strengths and weaknesses of various models and explore the trade-offs between model complexity and performance in different applications. Our work informs social and behavioral scientists of the challenges associated with text mining of large textual datasets, while providing best-practice recommendations. [ABSTRACT FROM AUTHOR]

Preparing future teachers to meet the demands of an increasingly dynamic world is a paramount challenge. Academic writing and critical thinking skills influence foreign language teachers' professional growth, shaping their students' cognitive development. This paper explores the integration of ChatGPT (generative pre-trained transformer) as a tool to augment future foreign language teachers' academic writing and critical thinking skills. Through engagement with ChatGPT, future foreign language teachers have the opportunity to interact with a large language model that can provide targeted feedback, prompt thought-provoking discussions, and assist in refining professionally oriented competencies. This study examines the impact of ChatGPT on skills development through a comprehensive analysis of empirical data, pedagogical frameworks, and student experiences. A qualitative study conducted with 35 students enrolled in a foreign languages master's program utilized focus group interviews and thematic analysis. The findings highlight ChatGPT's limitations in content generation while also recognizing its potential to reduce research labor and assist in formatting and referencing tasks. The study underscores the importance of informed usage of ChatGPT, with students and educators recognizing the necessity of verifying information and maintaining academic integrity. [ABSTRACT FROM AUTHOR]

Copyright of Revista de Ciencias Sociales (13159518) is the property of Revista de Ciencias Sociales de la Universidad del Zulia Venezuela and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

GPT-3 is a neuronal language model that performs tasks such as classification, question-answering and text summarization. Although chatbots like BlenderBot-3 work well in a conversational sense, and GPT-3 can assist experts in evaluating questions, they are quantifiably worse than real teachers in several pedagogical dimensions. We present the first systematic literature review that analyzes the main contributions and uses of GPT-3 in the field of education. The protocols suggested in the PRISMA 2020 statement were followed for the drafting of the review. According to the results, 34 significant productions were identified through a systematic search in ISI Web of Science, SCOPUS and Google Scholar. GPT-3 has been considered in the academic, ethical and medical fields, in humanities and in computer science, in the formulation of questions and answers, and through cooperative educational dialogs. GPT-3 has been proven to have valuable applications in education, such as the automation of routine tasks, in making quick diagnoses of the students' weaknesses and in the automatic generation of questions, but it still faces challenges and limitations that require additional investigation. We discuss the educational possibilities and the limitations to the use of GPT-3. [ABSTRACT FROM AUTHOR]

Copyright of Cuadernos del Centro de Estudios de Diseño y Comunicación is the property of Cuadernos del Centro de Estudios de Diseno y Comunicacion and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Recommender systems are a key technology for many applications, such as e-commerce, streaming media, and social media. Traditional recommender systems rely on collaborative filtering or content-based filtering to make recommendations. However, these approaches have limitations, such as the cold start and the data sparsity problem. This survey paper presents an in-depth analysis of the paradigm shift from conventional recommender systems to generative pre-trained-transformers-(GPT)-based chatbots. We highlight recent developments that leverage the power of GPT to create interactive and personalized conversational agents. By exploring natural language processing (NLP) and deep learning techniques, we investigate how GPT models can better understand user preferences and provide context-aware recommendations. The paper further evaluates the advantages and limitations of GPT-based recommender systems, comparing their performance with traditional methods. Additionally, we discuss potential future directions, including the role of reinforcement learning in refining the personalization aspect of these systems. [ABSTRACT FROM AUTHOR]

This paper introduces a novel method for collecting and translating texts from the Mixtec to the Spanish language. The method comprises four primary steps. First, we collected a Mixtec–Spanish corpus that includes 4568 sentences from educational and religious domain texts. To enhance the parallel corpus, we generate synthetic data with GPT-3.5. Second, we cleaned the data with a semi-automatic approach followed by preprocessing and tokenization. In preprocessing, we removed stop words, duplicated sentences, special characters, and numbers and converted them to lowercase. Third, we performed semi-automatic alignment to find the correspondence of Mixtec–Spanish sentences to generate sentence-level aligned texts necessary for translation. Finally, we trained automatic translation models based on recurrent neural networks, bidirectional recurrent neural networks, and Transformers. Our system achieved a BLEU score of 95.66 for Mixtec-to-Spanish translation and 99.87 for Spanish-to-Mixtec translation. We also obtained a translation edit rate (TER) of 0.5 for Spanish-to-Mixtec and a TER of 16.5 for Mixtec-to-Spanish. Our research stands out as a pioneering effort in the field of automatic Mixtec-to-Spanish translation in Mexico, filling a gap identified in the current literature. [ABSTRACT FROM AUTHOR]

Medical imaging description and disease diagnosis are vitally important yet time-consuming. Automated diagnosis report generation (DRG) from medical imaging description can reduce clinicians' workload and improve their routine efficiency. To address this natural language generation task, fine-tuning a pre-trained large language model (LLM) is cost-effective and indispensable, and its success has been witnessed in many downstream applications. However, semantic inconsistency of sentence embeddings has been massively observed from undesirable repetitions or unnaturalness in text generation. To address the underlying issue of anisotropic distribution of token representation, in this study, a contrastive learning penalized cross-entropy (CLpCE) objective function is implemented to enhance the semantic consistency and accuracy of token representation by guiding the fine-tuning procedure towards a specific task. Furthermore, to improve the diversity of token generation in text summarization and to prevent sampling from unreliable tail of token distributions, a diversity contrastive search (DCS) decoding method is designed for restricting the report generation derived from a probable candidate set with maintained semantic coherence. Furthermore, a novel metric named the maximum of token repetition ratio (maxTRR) is proposed to estimate the token diversity and to help determine the candidate output. Based on the LLM of a generative pre-trained Transformer 2 (GPT-2) of Chinese version, the proposed CLpCE with DCS (CLpCEwDCS) decoding framework is validated on 30,000 desensitized text samples from the "Medical Imaging Diagnosis Report Generation" track of 2023 Global Artificial Intelligence Technology Innovation Competition. Using four kinds of metrics evaluated from n-gram word matching, semantic relevance, and content similarity as well as the maxTRR metric extensive experiments reveal that the proposed framework effectively maintains semantic coherence and accuracy (BLEU-1, 0.4937; BLEU-2, 0.4107; BLEU-3, 0.3461; BLEU-4, 0.2933; METEOR, 0.2612; ROUGE, 0.5182; CIDER, 1.4339) and improves text generation diversity and naturalness (maxTRR, 0.12). The phenomenon of dull or repetitive text generation is common when fine-tuning pre-trained LLMs for natural language processing applications. This study might shed some light on relieving this issue by developing comprehensive strategies to enhance semantic coherence, accuracy and diversity of sentence embeddings. [ABSTRACT FROM AUTHOR]

Objectives The rapid advancement of Large Language Models (LLMs) has prompted an exploration of their efficacy in generating PICO-based (Patient, Intervention, Comparison, Outcome) queries, especially in the field of orthodontics. This study aimed to assess the usability of Large Language Models (LLMs), in aiding systematic review processes, with a specific focus on comparing the performance of ChatGPT 3.5 and ChatGPT 4 using a specialized prompt tailored for orthodontics. Materials/Methods Five databases were perused to curate a sample of 77 systematic reviews and meta-analyses published between 2016 and 2021. Utilizing prompt engineering techniques, the LLMs were directed to formulate PICO questions, Boolean queries, and relevant keywords. The outputs were subsequently evaluated for accuracy and consistency by independent researchers using three-point and six-point Likert scales. Furthermore, the PICO records of 41 studies, which were compatible with the PROSPERO records, were compared with the responses provided by the models. Results ChatGPT 3.5 and 4 showcased a consistent ability to craft PICO-based queries. Statistically significant differences in accuracy were observed in specific categories, with GPT-4 often outperforming GPT-3.5. Limitations The study's test set might not encapsulate the full range of LLM application scenarios. Emphasis on specific question types may also not reflect the complete capabilities of the models. Conclusions/Implications Both ChatGPT 3.5 and 4 can be pivotal tools for generating PICO-driven queries in orthodontics when optimally configured. However, the precision required in medical research necessitates a judicious and critical evaluation of LLM-generated outputs, advocating for a circumspect integration into scientific investigations. [ABSTRACT FROM AUTHOR]

Copyright of Romanian Journal of Information Technology & Automatic Control / Revista Română de Informatică și Automatică is the property of National Institute for Research & Development in Informatics - ICI Bucharest and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The main goal of the study is to identify factors influencing the formation of video game content through GTP models, and based on these factors to formulate strategies for improving these processes. The object of the research is digital information systems for creating the context of video games. The scientific task of the study is the formation and selection of the most optimal strategy for adapting an information system under the influence of negative factors for video game developers. The research methodology includes the use of a combined approach, including hierarchy analysis, pairwise comparison of alternatives, expert analysis and the Delphi method. As a result of this combined analysis and innovative methods, we developed and selected the most optimal strategy for optimal use of GPT models in video games, which takes into account both technological opportunities and challenges. The study has limitations because the strategies were formed on the basis of a certain list of factors, which theoretically could lead to failure to take into account secondary factors and elements that may also influence the area being studied. [ABSTRACT FROM AUTHOR]

This paper explores the emerging field of prompt engineering within generative AI, emphasizing its role as a critical intersection between art and science. Prompt engineering is identified as the key to unlocking the full potential of generative AI technologies by optimizing human-AI communication. Through a comprehensive analysis of the related literature, this study illustrates how prompt engineering transcends mere technical manipulation, requiring a blend of creativity, strategic thinking, and a deep understanding of generative AI capabilities. This paper provides various strategies for crafting effective prompts, from simple to sophisticated techniques, highlighting the importance of ethical considerations and the potential risks associated with prompt manipulation. By establishing a set of principles and guidelines, this paper aims to advance prompt engineering as a discipline essential for enhancing AI's functionality and reliability and, with this justification, introduces the 'Prompt Engineering for Gen[i]erative AI Framework'. After all, this paper calls for a multidisciplinary approach to prompt engineering, advocating for its recognition and development as a pivotal component of AI literacy and application. Through this exploration, this paper intends to contribute to the evolving dialogue on the integration of human creativity with generative AI capabilities, offering insights into the future of effective and ethical AI interaction. [ABSTRACT FROM AUTHOR]

Graphical passwords or passphrases (GPs) are examined as reliable authentication system over text-based passphrases. Several obtainable applications utilize GPs and image-based authentication schemes. Even though, these authentication methods experience an issue of managing image or pictorial data. Here, Natural Language Processing (NLP) + Stable Diffusion (SD)_graphical authentication is presented for graphical authentication using passphrase. The passphrase, removing stop words, spell check, similarity check, stemming and lemmatization, label encoder, positional embedding and encryption are the steps carried out in registration phase whereas decryption Advanced Encryption Standard (AES), sentence generation, image set generation and grid module are conducted in verification phase. Initially, passphrase is considered and then, stop words are removed from it. Thereafter, spell check as well as similarity check are done and after these processes stemming and lemmatization is performed. In label encoder, label is generated for individual word in passphrase. Afterwards, positional embedding is done and lastly, encryption is conducted in registration phase. In verification phase, encrypted passphrase is decrypted, sentence is generated utilizing Generative Pre-trained Transformer (GPT), image set is generated by SD model and finally, image grid module is accomplished. Moreover, NLP + SD_graphical authentication achieved minimum attack detection, login failure, login time about 0.598, 0.191, 14.175sec and maximum memorability about 0.932. [ABSTRACT FROM AUTHOR]

Conversational intelligence has grown substantially with the emergence of powerful natural language processing models, most notably ChatGPT, an OpenAI innovation built on the robust GPT-3.5 architecture. The paper investigates the capabilities and limitations of ChatGPT, with the goal of providing a nuanced assessment of its potential and problems within the area of conversational AI. To assess ChatGPT’s effectiveness across multiple domains, the study employs a varied dataset that includes general knowledge, contextual discussions, and specialized topics. Fluency, coherence, and contextual understanding evaluation measures are painstakingly applied alongside human evaluators to determine the model’s skill in providing contextually appropriate and coherent responses. The investigation sheds light on ChatGPT’s natural language processing, demonstrating its ability to comprehend a wide range of user inputs, including sophisticated language and idiomatic expressions. The model’s ability to retain context during long talks is investigated, revealing information on its ability to manage long-term dependencies and respond using historical context. [ABSTRACT FROM AUTHOR]

Copyright of Egyptian Journal of Information Sciences is the property of Beni Suef University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Emergent chain-of-thought (CoT) reasoning capabilities promise to improve the performance and explainability of large language models (LLMs). However, uncertainties remain about how reasoning strategies formulated for previous model generations generalize to new model generations and different datasets. In this small-scale study, we compare different reasoning strategies induced by zero-shot prompting across six recently released LLMs (davinci-002, davinci-003, GPT-3.5-turbo, GPT-4, Flan-T5-xxl and Cohere command-xlarge). We test them on six question-answering datasets that require real-world knowledge application and logical verbal reasoning, including datasets from scientific and medical domains. Our findings demonstrate that while some variations in effectiveness occur, gains from CoT reasoning strategies remain robust across different models and datasets. GPT-4 benefits the most from current state-of-the-art reasoning strategies and performs best by applying a prompt previously discovered through automated discovery. [ABSTRACT FROM AUTHOR]

Though Vaccines are instrumental in global health, mitigating infectious diseases and pandemic outbreaks, they can occasionally lead to adverse events (AEs). Recently, Large Language Models (LLMs) have shown promise in effectively identifying and cataloging AEs within clinical reports. Utilizing data from the Vaccine Adverse Event Reporting System (VAERS) from 1990 to 2016, this study particularly focuses on AEs to evaluate LLMs' capability for AE extraction. A variety of prevalent LLMs, including GPT-2, GPT-3 variants, GPT-4, and Llama2, were evaluated using Influenza vaccine as a use case. The fine-tuned GPT 3.5 model (AE-GPT) stood out with a 0.704 averaged micro F1 score for strict match and 0.816 for relaxed match. The encouraging performance of the AE-GPT underscores LLMs' potential in processing medical data, indicating a significant stride towards advanced AE detection, thus presumably generalizable to other AE extraction tasks. [ABSTRACT FROM AUTHOR]

This paper examines the implications of AI and machine translation on traditional lexicography, using three canonical scenarios for dictionary use: text reception, text production, and text translation as test cases. With the advent of high-capacity, AI-driven language models such as OpenAI's GPT-3 and GPT-4, and the efficacy of machine translation, the utility of conventional dictionaries comes under question. Despite these advancements, the study finds that lexicography remains relevant, especially for less-documented languages where AI falls short, but human lexicographers excel in data-sparse environments. It argues for the importance of lexicography in promoting linguistic diversity and maintaining the integrity of lesser-known languages. Moreover, as AI technologies progress, they present opportunities for lexicographers to expand their methodology and embrace interdisciplinarity. The role of lexicographers is likely to shift towards guiding and refining increasingly automated tools, ensuring ethical linguistic data use, and counteracting AI biases. [ABSTRACT FROM AUTHOR]