Search

We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document understanding. Our model is trained on a comprehensive instruction-following dataset, including document-related tasks, such as content extraction from tables, charts, diagrams, sketches, and infographics, as well as general image tasks. The architecture of Granite Vision is centered around visual modality alignment with a decoder-only, 2 billion parameter Granite large language model. Additionally, we introduce a dedicated safety classification approach in test-time that leverages a sparse set of attention vectors to identify potential harmful inputs. Despite its lightweight architecture, Granite Vision achieves strong results in standard benchmarks related to visual document understanding, as well as on the LiveXiv benchmark, which is designed to avoid test set contamination by using a constantly updated corpus of recently published Arxiv papers. We are releasing the model under the Apache-2 license, allowing for both research and commercial use, while offering complete visibility into the training data and other relevant details. See https://huggingface.co/ibm-granite/ for model weights.

We investigate under which circumstances there exists nonzero {\it{projective}} smooth $\field[G]$-modules, where $\field$ is a field of characteristic $p$ and $G$ is a locally pro-$p$ group. We prove the non-existence of (non-trivial) projective objects for so-called {\it{fair}} groups -- a family including $\bf{G}(\frak{F})$ for a connected reductive group $\bf{G}$ defined over a non-archimedean local field $\frak{F}$. This was proved in \cite{SS24} for finite extensions $\frak{F}/\Bbb{Q}_p$. The argument we present in this note has the benefit of being completely elementary and, perhaps more importantly, adaptable to $\frak{F}=\Bbb{F}_q(\!(t)\!)$. Finally, we elucidate the fairness condition via a criterion in the Chabauty space of $G$., Comment: 12 pages

Sparse retrieval methods like BM25 are based on lexical overlap, focusing on the surface form of the terms that appear in the query and the document. The use of inverted indices in these methods leads to high retrieval efficiency. On the other hand, dense retrieval methods are based on learned dense vectors and, consequently, are effective but comparatively slow. Since sparse and dense methods approach problems differently and use complementary relevance signals, approximation methods were proposed to balance effectiveness and efficiency. For efficiency, approximation methods like HNSW are frequently used to approximate exhaustive dense retrieval. However, approximation techniques still exhibit considerably higher latency than sparse approaches. We propose LexBoost that first builds a network of dense neighbors (a corpus graph) using a dense retrieval approach while indexing. Then, during retrieval, we consider both a document's lexical relevance scores and its neighbors' scores to rank the documents. In LexBoost this remarkably simple application of the Cluster Hypothesis contributes to stronger ranking effectiveness while contributing little computational overhead (since the corpus graph is constructed offline). The method is robust across the number of neighbors considered, various fusion parameters for determining the scores, and different dataset construction methods. We also show that re-ranking on top of LexBoost outperforms traditional dense re-ranking and leads to results comparable with higher-latency exhaustive dense retrieval., Comment: ACM DocEng 2024

Generative language models hallucinate. That is, at times, they generate factually flawed responses. These inaccuracies are particularly insidious because the responses are fluent and well-articulated. We focus on the task of Grounded Answer Generation (part of Generative IR), which aims to produce direct answers to a user's question based on results retrieved from a search engine. We address hallucination by adapting an existing genetic generation approach with a new 'balanced fitness function' consisting of a cross-encoder model for relevance and an n-gram overlap metric to promote grounding. Our balanced fitness function approach quadruples the grounded answer generation accuracy while maintaining high relevance., Comment: Gen-IR@SIGIR 2024

This study focuses on inverting time-domain airborne electromagnetic data in 2D by training a neural-network to understand the relationship between data and conductivity, thereby removing the need for expensive forward modeling during the inversion process. Instead the forward modeling is completed in the training stage, where training models are built before calculating 3D forward modeling training data. The method relies on training data being similar to the field dataset of choice, therefore, the field data was first inverted in 1D to get an idea of the expected conductivity distribution. With this information, $ 10,000 $ training models were built with similar conductivity ranges, and the research shows that this provided enough information for the network to produce realistic 2D inversion models over an aquifer-bearing region in California. Once the training was completed, the actual inversion time took only a matter of seconds on a generic laptop, which means that if future data was collected in this region it could be inverted in near real-time. Better results are expected by increasing the number of training models and eventually the goal is to extend the method to 3D inversion., Comment: 4 pages, 5 figures, conference submission

In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains. This effort has attracted substantial interest from both industry and academy, highlighting its significance in the current technological landscape. Most datasets in this area are primarily focused on Key Information Extraction (KIE), where the extraction process revolves around extracting information using a specific, predefined set of keys. Unlike most existing datasets and benchmarks, our focus is on discovering key-value pairs (KVPs) without relying on predefined keys, navigating through an array of diverse templates and complex layouts. This task presents unique challenges, primarily due to the absence of comprehensive datasets and benchmarks tailored for non-predetermined KVP extraction. To address this gap, we introduce KVP10k , a new dataset and benchmark specifically designed for KVP extraction. The dataset contains 10707 richly annotated images. In our benchmark, we also introduce a new challenging task that combines elements of KIE as well as KVP in a single task. KVP10k sets itself apart with its extensive diversity in data and richly detailed annotations, paving the way for advancements in the field of information extraction from complex business documents., Comment: accepted ICDAR2024

Background: Recent advancements in Artificial Intelligence (AI) contributed significantly to suicide assessment, however, our theoretical understanding of this complex behavior is still limited. Objective: This study aimed to harness AI methodologies to uncover hidden risk factors that trigger or aggravate suicide behaviors. Method: The primary dataset included 228,052 Facebook postings by 1,006 users who completed the gold-standard Columbia Suicide Severity Rating Scale. This dataset was analyzed using a bottom-up research pipeline without a-priory hypotheses and its findings were validated using a top-down analysis of a new dataset. This secondary dataset included responses by 1,062 participants to the same suicide scale as well as to well-validated scales measuring depression and boredom. Results: An almost fully automated, AI-guided research pipeline resulted in four Facebook topics that predicted the risk of suicide, of which the strongest predictor was boredom. A comprehensive literature review using APA PsycInfo revealed that boredom is rarely perceived as a unique risk factor of suicide. A complementing top-down path analysis of the secondary dataset uncovered an indirect relationship between boredom and suicide, which was mediated by depression. An equivalent mediated relationship was observed in the primary Facebook dataset as well. However, here, a direct relationship between boredom and suicide risk was also observed. Conclusions: Integrating AI methods allowed the discovery of an under-researched risk factor of suicide. The study signals boredom as a maladaptive 'ingredient' that might trigger suicide behaviors, regardless of depression. Further studies are recommended to direct clinicians' attention to this burdening, and sometimes existential experience.

This contribution presents the recent research developments within the Cosmic Ray Extremely Distributed Observatory (CREDO) in the search for resolution of various scientific puzzles, ranging from fundamental physical questions to applications like the determination of earthquake precursors. The state-of-the art theoretical, numerical and computational aspects of these phenomena are addressed, as well as recent experimental developments for detection., Comment: 9 pages, 7 figures. Based on the contribution to the XVIII Mexican Workshop on Particles and Fields in Puebla, Mexico, November 2022. M\'exico

There is a large volume of late antique and medieval Hebrew texts. They represent a crucial linguistic and cultural bridge between Biblical and modern Hebrew. Poetry is prominent in these texts and one of its main haracteristics is the frequent use of metaphor. Distinguishing figurative and literal language use is a major task for scholars of the Humanities, especially in the fields of literature, linguistics, and hermeneutics. This paper presents a new, challenging dataset of late antique and medieval Hebrew poetry with expert annotations of metaphor, as well as some baseline results, which we hope will facilitate further research in this area., Comment: EACL 2024. Project webpage: https://tokeron.github.io/metaphor/

Consider a commutative unital ring $A$ and a unital $A$-algebra $R$. Let $d$ be a positive integer. Chenevier proved that when $(2d)!$ is invertible in $A$, the map associating to a determinant its trace is a bijection between $A$-valued $d$-dimensional determinants of $R$ and $A$-valued $d$-dimensional pseudocharacters of $R$. In this paper, we show that assuming $d!$ is invertible in $A$ is sufficient. This assumption is already made in the definition of a $d$-dimensional pseudocharacter. Our proof involves establishing a product formula for pseudocharacters, which might be of independent interest., Comment: 7 pages

Queer youth face increased mental health risks, such as depression, anxiety, and suicidal ideation. Hindered by negative stigma, they often avoid seeking help and rely on online resources, which may provide incompatible information. Although access to a supportive environment and reliable information is invaluable, many queer youth worldwide have no access to such support. However, this could soon change due to the rapid adoption of Large Language Models (LLMs) such as ChatGPT. This paper aims to comprehensively explore the potential of LLMs to revolutionize emotional support for queers. To this end, we conduct a qualitative and quantitative analysis of LLM's interactions with queer-related content. To evaluate response quality, we develop a novel ten-question scale that is inspired by psychological standards and expert input. We apply this scale to score several LLMs and human comments to posts where queer youth seek advice and share experiences. We find that LLM responses are supportive and inclusive, outscoring humans. However, they tend to be generic, not empathetic enough, and lack personalization, resulting in nonreliable and potentially harmful advice. We discuss these challenges, demonstrate that a dedicated prompt can improve the performance, and propose a blueprint of an LLM-supporter that actively (but sensitively) seeks user context to provide personalized, empathetic, and reliable responses. Our annotated dataset is available for further research.

Large Language Models (LLMs) have spurred progress in text-to-SQL, the task of generating SQL queries from natural language questions based on a given database schema. Despite the declarative nature of SQL, it continues to be a complex programming language. In this paper, we investigate the potential of an alternative query language with simpler syntax and modular specification of complex queries. The purpose is to create a query language that can be learned more easily by modern neural semantic parsing architectures while also enabling non-programmers to better assess the validity of the query plans produced by an interactive query plan assistant. The proposed alternative query language is called Query Plan Language (QPL). It is designed to be modular and can be translated into a restricted form of SQL Common Table Expressions (CTEs). The aim of QPL is to make complex data retrieval accessible to non-programmers by allowing users to express their questions in natural language while also providing an easier-to-verify target language. The paper demonstrates how neural LLMs can benefit from QPL's modularity to generate complex query plans in a compositional manner. This involves a question decomposition strategy and a planning stage. We conduct experiments on a version of the Spider text-to-SQL dataset that has been converted to QPL. The hierarchical structure of QPL programs enables us to measure query complexity naturally. Based on this assessment, we identify the low accuracy of existing text-to-SQL systems on complex compositional queries. We present ways to address the challenge of complex queries in an iterative, user-controlled manner, using fine-tuned LLMs and a variety of prompting strategies in a compositional manner., Comment: arXiv admin note: text overlap with arXiv:2310.13575

Text-to-SQL semantic parsing faces challenges in generalizing to cross-domain and complex queries. Recent research has employed a question decomposition strategy to enhance the parsing of complex SQL queries. However, this strategy encounters two major obstacles: (1) existing datasets lack question decomposition; (2) due to the syntactic complexity of SQL, most complex queries cannot be disentangled into sub-queries that can be readily recomposed. To address these challenges, we propose a new modular Query Plan Language (QPL) that systematically decomposes SQL queries into simple and regular sub-queries. We develop a translator from SQL to QPL by leveraging analysis of SQL server query optimization plans, and we augment the Spider dataset with QPL programs. Experimental results demonstrate that the modular nature of QPL benefits existing semantic-parsing architectures, and training text-to-QPL parsers is more effective than text-to-SQL parsing for semantically equivalent queries. The QPL approach offers two additional advantages: (1) QPL programs can be paraphrased as simple questions, which allows us to create a dataset of (complex question, decomposed questions). Training on this dataset, we obtain a Question Decomposer for data retrieval that is sensitive to database schemas. (2) QPL is more accessible to non-experts for complex queries, leading to more interpretable output from the semantic parser., Comment: EMNLP 2023 Findings

In this contribution we study the possibility of the formation of cosmic ray ensembles (CRE) created by the interaction of ultra-high energy (UHE) photons with the magnetic field of the Sun. The lack of observation of those UHE and the difficulties for their identification given the current methodologies motivates this study. We performed simulations using the PRESHOWER program in order to simulate the expected extensive air showers which might be spatially correlated generated upon entering the Earth's atmosphere. We found characteristic features like very thing and extremely elongates cascades of secondary photons with their corresponding energies spanning the entire cosmic range spectrum. Shower footprints are as large as hundreds of kilometres. An application of this study is the scenario of gamma-ray emission from the vicinity of the Sun as a result of ultra-high energy photon cascading in the solar magnetic field in order to understand recent observations made by the HAWC and Fermi-LAT observatories., Comment: 8 pages, 4 figures, 38th International Cosmic Ray Conference (ICRC2023) 26 July - 3 August, 2023 Nagoya, Japan

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on maximizing a reward function, which typically captures general trends but cannot precisely capture, or rule out, certain behaviors of the system. In this paper, we propose a novel framework aimed at drastically reducing the undesirable behavior of DRL-based software, while maintaining its excellent performance. In addition, our framework can assist in providing engineers with a comprehensible characterization of such undesirable behavior. Under the hood, our approach is based on extracting decision tree classifiers from erroneous state-action pairs, and then integrating these trees into the DRL training loop, penalizing the system whenever it performs an error. We provide a proof-of-concept implementation of our approach, and use it to evaluate the technique on three significant case studies. We find that our approach can extend existing frameworks in a straightforward manner, and incurs only a slight overhead in training time. Further, it incurs only a very slight hit to performance, or even in some cases - improves it, while significantly reducing the frequency of undesirable behavior.

Retrieval approaches that score documents based on learned dense vectors (i.e., dense retrieval) rather than lexical signals (i.e., conventional retrieval) are increasingly popular. Their ability to identify related documents that do not necessarily contain the same terms as those appearing in the user's query (thereby improving recall) is one of their key advantages. However, to actually achieve these gains, dense retrieval approaches typically require an exhaustive search over the document collection, making them considerably more expensive at query-time than conventional lexical approaches. Several techniques aim to reduce this computational overhead by approximating the results of a full dense retriever. Although these approaches reasonably approximate the top results, they suffer in terms of recall -- one of the key advantages of dense retrieval. We introduce 'LADR' (Lexically-Accelerated Dense Retrieval), a simple-yet-effective approach that improves the efficiency of existing dense retrieval models without compromising on retrieval effectiveness. LADR uses lexical retrieval techniques to seed a dense retrieval exploration that uses a document proximity graph. We explore two variants of LADR: a proactive approach that expands the search space to the neighbors of all seed documents, and an adaptive approach that selectively searches the documents with the highest estimated relevance in an iterative fashion. Through extensive experiments across a variety of dense retrieval models, we find that LADR establishes a new dense retrieval effectiveness-efficiency Pareto frontier among approximate k nearest neighbor techniques. Further, we find that when tuned to take around 8ms per query in retrieval latency on our hardware, LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks., Comment: SIGIR 2023

The brain is likely the most complex organ, given the variety of functions it controls, the number of cells it comprises, and their corresponding diversity. Studying and identifying neurons, the brain's primary building blocks, is a crucial milestone and essential for understanding brain function in health and disease. Recent developments in machine learning have provided advanced abilities for classifying neurons. However, these methods remain black boxes with no explainability and reasoning. This paper aims to provide a robust and explainable deep-learning framework to classify neurons based on their electrophysiological activity. Our analysis is performed on data provided by the Allen Cell Types database containing a survey of biological features derived from single-cell recordings of mice and humans. First, we classify neuronal cell types of mice data to identify excitatory and inhibitory neurons. Then, neurons are categorized to their broad types in humans using domain adaptation from mice data. Lastly, neurons are classified into sub-types based on transgenic mouse lines using deep neural networks in an explainable fashion. We show state-of-the-art results in a dendrite-type classification of excitatory vs. inhibitory neurons and transgenic mouse lines classification. The model is also inherently interpretable, revealing the correlations between neuronal types and their electrophysiological properties.