Search

The use of creative writing as training data for large language models (LLMS) is highly contentious. While some argue that such use constitutes "fair use" and therefore does not require consent or compensation, others argue that consent and compensation is the morally correct approach. In this paper, we seek to understand how creative writers reason about the real or hypothetical use of their writing as training data and under what conditions, if any, they would consent to their writing being used. We interviewed 33 writers with variation across genre, method of publishing, degree of professionalization, and attitudes toward and engagement with LLMs. Through a grounded theory analysis, we report on core principles that writers express and how these principles can be at odds with their realistic expectations for how institutions engage with their work.

4H Silicon Carbide (4H-SiC) combines many attractive properties such as a high carrier mobility, a wide bandgap, and a high thermal conductivity, making it an ideal candidate for high-power electronic devices. However, a primary challenge in utilizing 4H-SiC is the presence of defects in epitaxial layers, which can significantly degrade device performance. In this study, we have used X-ray transmission topography with a rocking curve imaging technique to characterize the types and distribution of defects in 4H-SiC. The derived maps from the fitted Gaussian parameters were used to investigate dislocations in 4H-SiC. Understanding the distribution of the dislocations provides valuable insights into the overall crystal quality, which can guide improvements for the fabrication processes.

We investigate the role of topological defects in exciton behavior in (6,5) semiconducting single-walled carbon nanotubes using density functional theory. Our study identifies the helical Stone-Wales defect as a prominent trap for triplet excitons, characterized by a large zero-field splitting consistent with experimental data and a small singlet-triplet gap. The weak electron-phonon coupling, as evidenced by a Huang-Rhys factor of 0.74, renders it a promising single-photon emitter, with the zero-phonon line predicted at 1.6 $\mu$m, within the telecom range. These insights into defect-engineered electronic structure and exciton dynamics offer promising opportunities for improving the performance of carbon nanotube-based quantum light sources and optoelectronic devices.

We present a formalism for computing arbitrary multi-loop Feynman graphs in curved spacetime using the heat kernel approach. To this end, we compute the off-diagonal components of the heat kernel in Riemann normal coordinates up to second order in the curvature.

Process models are, like event data, first-class citizens in most process mining approaches. Several process modeling formalisms have been proposed and used, e.g., Petri nets, BPMN, and process trees. Despite their frequent use, little research addresses the formal properties of process trees and the corresponding potential to improve the efficiency of solving common computational problems. Therefore, in this paper, we propose an invertible state space definition for process trees and demonstrate that the corresponding state space graph is isomorphic to the state space graph of the tree's inverse. Our result supports the development of novel, time-efficient, decomposition strategies for applications of process trees. Our experiments confirm that our state space definition allows for the adoption of bidirectional state space search, which significantly improves the overall performance of state space searches., Comment: 8 pages, 7 figures

A key technology in sperm whale (Physeter macrocephalus) monitoring is the identification of sperm whale communication signals, known as codas. In this paper we present the first automatic coda detector and annotator. The main innovation in our detector is graph-based clustering, which utilizes the expected similarity between the clicks that make up the coda. Results show detection and accurate annotation at low signal-to-noise ratios, separation between codas and echolocation clicks, and discrimination between codas from simultaneously emitting whales. Using this automatic annotator, insights into the characterization of sperm whale communication are presented. The results include new types of coda signals, analyzes of the distribution of coda types among different whales and for different years, and evidence for synchronization between communicating whales in terms of coda type and coda transmission time. These results indicate a high degree of complexity in the communication system of this cetacean species. To ensure traceability, we share the implementation code of our coda detector.

We propose a general approach to find an optimal representation of a quantum many body wave function for a given error margin via global fermionic mode optimization. The stationary point on a fixed rank matrix product state manifold is obtained via a joint optimization on the Grassman manifold [Phys. Rev. Lett. 117, 210402] together with swap gates controlled permutations. The minimization of the global quantity, the block entropy area, guarantees that the method fulfills all criteria with respect to partial derivatives. Numerical results via large scale density matrix renormalization group simulations on strongly correlated molecular systems and two-dimensional fermionic lattice models are discussed., Comment: 5 pages, 4 figures

This study identifies a gap in data-driven approaches to robot-centric pedestrian interactions and proposes a corresponding pipeline. The pipeline utilizes unsupervised learning techniques to identify patterns in interaction data of urban environments, specifically focusing on conflict scenarios. Analyzed features include the robot's and pedestrian's speed and contextual parameters such as proximity to intersections. They are extracted and reduced in dimensionality using Principal Component Analysis (PCA). Finally, K-means clustering is employed to uncover underlying patterns in the interaction data. A use case application of the pipeline is presented, utilizing real-world robot mission data from a mid-sized German city. The results indicate the need for enriching interaction representations with contextual information to enable fine-grained analysis and reasoning. Nevertheless, they also highlight the need for expanding the data set and incorporating additional contextual factors to enhance the robots situational awareness and interaction quality.

We study barycenters of $N$ probability measures on $\mathbb{R}^d$ with respect to the $p$-Wasserstein metric ($1

New capabilities in foundation models are owed in large part to massive, widely-sourced, and under-documented training data collections. Existing practices in data collection have led to challenges in tracing authenticity, verifying consent, preserving privacy, addressing representation and bias, respecting copyright, and overall developing ethical and trustworthy foundation models. In response, regulation is emphasizing the need for training data transparency to understand foundation models' limitations. Based on a large-scale analysis of the foundation model training data landscape and existing solutions, we identify the missing infrastructure to facilitate responsible foundation model development practices. We examine the current shortcomings of common tools for tracing data authenticity, consent, and documentation, and outline how policymakers, developers, and data creators can facilitate responsible foundation model development by adopting universal data provenance standards., Comment: ICML 2024 camera-ready version (Spotlight paper). 9 pages, 2 tables

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants., Comment: Published as a conference paper at CHI 2024

Summarizing clinical text is crucial in health decision-support and clinical research. Large language models (LLMs) have shown the potential to generate accurate clinical text summaries, but still struggle with issues regarding grounding and evaluation, especially in safety-critical domains such as health. Holistically evaluating text summaries is challenging because they may contain unsubstantiated information. Here, we explore a general mitigation framework using Attribute Structuring (AS), which structures the summary evaluation process. It decomposes the evaluation process into a grounded procedure that uses an LLM for relatively simple structuring and scoring tasks, rather than the full task of holistic summary evaluation. Experiments show that AS consistently improves the correspondence between human annotations and automated metrics in clinical text summarization. Additionally, AS yields interpretations in the form of a short text span corresponding to each output, which enables efficient human auditing, paving the way towards trustworthy evaluation of clinical information in resource-constrained scenarios. We release our code, prompts, and an open-source benchmark at https://github.com/microsoft/attribute-structuring., Comment: 4 pages

Generative AI brings novel and impressive abilities to help people in everyday tasks. There are many AI workflows that solve real and complex problems by chaining AI outputs together with human interaction. Although there is an undeniable lure of AI, it is uncertain how useful generative AI workflows are after the novelty wears off. Additionally, workflows built with generative AI have the potential to be easily customized to fit users' individual needs, but do users take advantage of this? We conducted a three-week longitudinal study with 12 users to understand the familiarization and customization of generative AI tools for science communication. Our study revealed that there exists a familiarization phase, during which users were exploring the novel capabilities of the workflow and discovering which aspects they found useful. After this phase, users understood the workflow and were able to anticipate the outputs. Surprisingly, after familiarization the perceived utility of the system was rated higher than before, indicating that the perceived utility of AI is not just a novelty effect. The increase in benefits mainly comes from end-users' ability to customize prompts, and thus potentially appropriate the system to their own needs. This points to a future where generative AI systems can allow us to design for appropriation., Comment: 22 pages, 16 figures. ACM Conference on Designing Interactive Systems (DIS 2024)

Large language models (LLMs) are capable of generating multiple responses to a single prompt, yet little effort has been expended to help end-users or system designers make use of this capability. In this paper, we explore how to present many LLM responses at once. We design five features, which include both pre-existing and novel methods for computing similarities and differences across textual documents, as well as how to render their outputs. We report on a controlled user study (n=24) and eight case studies evaluating these features and how they support users in different tasks. We find that the features support a wide variety of sensemaking tasks and even make tasks previously considered to be too difficult by our participants now tractable. Finally, we present design guidelines to inform future explorations of new LLM interfaces., Comment: 34 pages, 13 figures, conditionally accepted to ACM Conference on Human Factors in Computing Systems 2024

We present fast simulation methods for the self-assembly of complex shapes in two dimensions. The shapes are modeled via a general boundary curve and interact via a standard volume term promoting overlap and an interpenetration penalty. To efficiently realize the Gibbs measure on the space of possible configurations we employ the hybrid Monte Carlo algorithm together with a careful use of signed distance functions for energy evaluation. Motivated by the self-assembly of identical coat proteins of the tobacco mosaic virus which assemble into a helical shell, we design a particular nonconvex 2D model shape and demonstrate its robust self-assembly into a unique final state. Our numerical experiments reveal two essential prerequisites for this self-assembly process: blocking and matching (i.e., local repulsion and attraction) of different parts of the boundary; and nonconvexity and handedness of the shape.

We implement AntClust, a clustering algorithm based on the chemical recognition system of ants and use it to cluster images of cars. We will give a short recap summary of the main working principles of the algorithm as devised by the original paper [1]. Further, we will describe how to define a similarity function for images and how the implementation is used to cluster images of cars from the vehicle re-identification data set. We then test the clustering performance of AntClust against DBSCAN, HDBSCAN and OPTICS. Finally one of the core parts in AntClust, the rule set can be easily redefined with our implementation, enabling a way for other bio-inspired algorithms to find rules in an automated process. The implementation can be found on GitLab [9]., Comment: 9 pages, 1 figure, conference paper

Medical text generation aims to assist with administrative work and highlight salient information to support decision-making. To reflect the specific requirements of medical text, in this paper, we propose a set of metrics to evaluate the completeness, conciseness, and attribution of the generated text at a fine-grained level. The metrics can be computed by various types of evaluators including instruction-following (both proprietary and open-source) and supervised entailment models. We demonstrate the effectiveness of the resulting framework, DocLens, with three evaluators on three tasks: clinical note generation, radiology report summarization, and patient question summarization. A comprehensive human study shows that DocLens exhibits substantially higher agreement with the judgments of medical experts than existing metrics. The results also highlight the need to improve open-source evaluators and suggest potential directions., Comment: ACL Camera Ready Version

The rapid digitization of real-world data offers an unprecedented opportunity for optimizing healthcare delivery and accelerating biomedical discovery. In practice, however, such data is most abundantly available in unstructured forms, such as clinical notes in electronic medical records (EMRs), and it is generally plagued by confounders. In this paper, we present TRIALSCOPE, a unifying framework for distilling real-world evidence from population-level observational data. TRIALSCOPE leverages biomedical language models to structure clinical text at scale, employs advanced probabilistic modeling for denoising and imputation, and incorporates state-of-the-art causal inference techniques to combat common confounders. Using clinical trial specification as generic representation, TRIALSCOPE provides a turn-key solution to generate and reason with clinical hypotheses using observational data. In extensive experiments and analyses on a large-scale real-world dataset with over one million cancer patients from a large US healthcare network, we show that TRIALSCOPE can produce high-quality structuring of real-world data and generates comparable results to marquee cancer trials. In addition to facilitating in-silicon clinical trial design and optimization, TRIALSCOPE may be used to empower synthetic controls, pragmatic trials, post-market surveillance, as well as support fine-grained patient-like-me reasoning in precision diagnosis and treatment., Comment: 6 Figures, 22 Pages, 3 Tables