Related papers: Agent-Specific Deontic Modality Detection in Legal…

Implementing smart contracts to automate the performance of high-value over-the-counter (OTC) financial derivatives is a formidable challenge. Due to the regulatory framework and the scale of financial risk if a contract were to go wrong,…

Deductive coding is a widely used qualitative research method for determining the prevalence of themes across documents. While useful, deductive coding is often burdensome and time consuming since it requires researchers to read, interpret,…

Summarizing long, domain-specific documents with large language models (LLMs) remains challenging due to context limitations, information loss, and hallucinations, particularly in clinical and legal settings. We propose a Discrete Wavelet…

Large Language Models (LLMs), trained on extensive datasets from the web, exhibit remarkable general reasoning skills. Despite this, they often struggle in specialized areas like law, mainly because they lack domain-specific pretraining.…

Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominantly rely on…

Decision conferences are structured, collaborative meetings that bring together experts from various fields to address complex issues and reach a consensus on recommendations for future actions or policies. These conferences often rely on…

Document fraud poses a significant threat to industries reliant on secure and verifiable documentation, necessitating robust detection mechanisms. This study investigates the efficacy of state-of-the-art multi-modal large language models…

Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference. We…

Pretrained transformer models have achieved state-of-the-art results in many tasks and benchmarks recently. Many state-of-the-art Language Models (LMs), however, do not scale well above the threshold of 512 input tokens. In specialized…

Documents are central to many business systems, and include forms, reports, contracts, invoices or purchase orders. The information in documents is typically in natural language, but can be organized in various layouts and formats. There…

E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models remain vulnerable to evasive content, which refers to inputs…

We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a…

The potential of large language models (LLMs) in specialized domains such as legal risk analysis remains underexplored. In response to growing interest in locally deploying open-source LLMs for legal tasks while preserving data…

Skill discovery methods enable agents to learn diverse emergent behaviors without explicit rewards. To make learned skills useful for unknown downstream tasks, obtaining a semantically diverse repertoire of skills is essential. While some…

Legal dispute analysis is crucial for intelligent legal assistance systems. However, current LLMs face significant challenges in understanding complex legal concepts, maintaining reasoning consistency, and accurately citing legal sources.…

Large Language Models (LLMs) have achieved remarkable progress in code-related tasks. Despite their advancement, empirical evidence reveals that they still struggle with \emph{deductive code reasoning}, the ability to reason about the…

This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for translation of plain text, we collect XML-structured parallel text…

Many specialized domains remain untouched by deep learning, as large labeled datasets require expensive expert annotators. We address this bottleneck within the legal domain by introducing the Contract Understanding Atticus Dataset (CUAD),…

In an era dominated by Large Language Models (LLMs), understanding their capabilities and limitations, especially in high-stakes fields like law, is crucial. While LLMs such as Meta's LLaMA, OpenAI's ChatGPT, Google's Gemini, DeepSeek, and…

Large Language Models (LLMs) suffer from hallucinations and factual inaccuracies, especially in complex reasoning and fact verification tasks. Multi-Agent Debate (MAD) systems aim to improve answer accuracy by enabling multiple LLM agents…