相关论文: ACORD: An Expert-Annotated Retrieval Dataset for L…

In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects. State-of-the-art methods rely on explicit mappings between claims and premises, and thus are unable to utilize large…

Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly…

Case law retrieval is the retrieval of judicial decisions relevant to a legal question. Case law retrieval comprises a significant amount of a lawyer's time, and is important to ensure accurate advice and reduce workload. We survey methods…

The task of expert finding has been getting increasing attention in information retrieval literature. However, the current state-of-the-art is still lacking in principled approaches for combining different sources of evidence in an optimal…

Abstractive compression utilizes smaller langauge models to condense query-relevant context, reducing computational costs in retrieval-augmented generation (RAG). However, retrieved documents often include information that is either…

Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belong. With not much prior work being done toward the…

Legal teams increasingly use machine learning to triage large volumes of contractual evidence, but many models are opaque, non-deterministic, and difficult to align with frameworks such as HIPAA or NERC-CIP. We study a simple, reproducible…

LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks…

We present an approach for modelling the structure and coarse content of legal documents with a view to providing automated support for the drafting of contracts and contract database retrieval. The approach is designed to be applicable…

Retrieval-Augmented Generation has made significant progress in the field of natural language processing. By combining the advantages of information retrieval and large language models, RAG can generate relevant and contextually appropriate…

This paper presents a link analysis approach for identifying privileged documents by constructing a network of human entities derived from email header metadata. Entities are classified as either counsel or non-counsel based on a predefined…

Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These pathways routinely fall short for the long tail of real-world care not covered by…

The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with…

Legal consultation is inherently iterative: before giving advice, a system must identify relevant legal elements, gather missing facts and authorities, and determine whether the current evidence is sufficient. Existing retrieval-augmented…

Companies regularly spend millions of dollars producing electronically-stored documents in legal matters. Recently, parties on both sides of the 'legal aisle' are accepting the use of machine learning techniques like text classification to…

Document-level relation extraction (DocRE) predicts relations for entity pairs that rely on long-range context-dependent reasoning in a document. As a typical multi-label classification problem, DocRE faces the challenge of effectively…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

We consider the problem of jointly training structured models for extraction from sources whose instances enjoy partial overlap. This has important applications like user-driven ad-hoc information extraction on the web. Such applications…

Human-annotated preference data play an important role in aligning large language models (LLMs). In this paper, we study two connected questions: how to monitor the quality of human preference annotators and how to incentivize them to…

Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and…