Explaining Legal Concepts with Augmented Large Language Models (GPT-4)

• URL: http://arxiv.org/abs/2306.09525v2
• Date: Thu, 22 Jun 2023 11:30:13 GMT
• Title: Explaining Legal Concepts with Augmented Large Language Models (GPT-4)
• Abstract summary: We evaluate the performance of GPT-4 in generating factually accurate, clear and relevant explanations of terms in legislation. We found that the direct application of GPT-4 yields explanations that appear to be of very high quality on their surface. We found that the augmentation leads to improved quality, and appears to eliminate the issue of hallucination.
• Score: 0.8924669503280334
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interpreting the meaning of legal open-textured terms is a key task of legal professionals. An important source for this interpretation is how the term was applied in previous court cases. In this paper, we evaluate the performance of GPT-4 in generating factually accurate, clear and relevant explanations of terms in legislation. We compare the performance of a baseline setup, where GPT-4 is directly asked to explain a legal term, to an augmented approach, where a legal information retrieval module is used to provide relevant context to the model, in the form of sentences from case law. We found that the direct application of GPT-4 yields explanations that appear to be of very high quality on their surface. However, detailed analysis uncovered limitations in terms of the factual accuracy of the explanations. Further, we found that the augmentation leads to improved quality, and appears to eliminate the issue of hallucination, where models invent incorrect statements. These findings open the door to the building of systems that can autonomously retrieve relevant sentences from case law and condense them into a useful explanation for legal scholars, educators or practicing lawyers alike.

Related papers

• WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report [55.27414605169639]
  We present WisdomInterrogatory (LuWen), an open-source Chinese legal language model built upon the Baichuan foundation model.<n>We evaluate LuWen on five representative legal tasks spanning both prediction and generation settings.
  arXiv  Detail & Related papers  (2026-04-08T06:59:07Z)
• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• Chinese Labor Law Large Language Model Benchmark [11.552694592413303]
  We present LabourLawLLM, a large language model tailored to Chinese labor law.<n>We also introduce LabourLawBench, a benchmark covering diverse labor-law tasks.<n> Experiments show that LabourLawLLM consistently outperforms general-purpose and existing legal-specific LLMs.
  arXiv  Detail & Related papers  (2026-01-15T01:27:29Z)
• Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics [49.3262123849242]
  We introduce LEGIT (LEGal Issue Trees), a novel large-scale (24K instances) expert-level legal reasoning dataset.<n>We convert court judgments into hierarchical trees of opposing parties' arguments and the court's conclusions, which serve as rubrics for evaluating the issue coverage and correctness of the reasoning traces.
  arXiv  Detail & Related papers  (2025-11-30T18:32:43Z)
• Capturing Legal Reasoning Paths from Facts to Law in Court Judgments using Knowledge Graphs [0.0]
  Court judgments reveal how legal rules have been interpreted and applied to facts.<n>Existing automated approaches for capturing legal reasoning do not accurately trace how facts relate to legal norms.<n>This paper builds a legal knowledge graph from 648 Japanese administrative court decisions.
  arXiv  Detail & Related papers  (2025-08-24T12:51:40Z)
• ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation [56.79698529022327]
  Legal claims refer to the plaintiff's demands in a case and are essential to guiding judicial reasoning and case resolution.<n>This paper explores the problem of legal claim generation based on the given case's facts.<n>We construct ClaimGen-CN, the first dataset for Chinese legal claim generation task.
  arXiv  Detail & Related papers  (2025-08-24T07:19:25Z)
• GLARE: Agentic Reasoning for Legal Judgment Prediction [60.13483016810707]
  Legal judgment prediction (LJP) has become increasingly important in the legal field.<n>Existing large language models (LLMs) have significant problems of insufficient reasoning due to a lack of legal knowledge.<n>We introduce GLARE, an agentic legal reasoning framework that dynamically acquires key legal knowledge by invoking different modules.
  arXiv  Detail & Related papers  (2025-08-22T13:38:12Z)
• GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant [0.0]
  We discuss the history of legal information retrieval, the difference between case law and statute law, its impact on the legal tasks and analyze the latest research in this field.<n>We propose a retrieval mechanism which is more explainable, human-friendly and achieves better results than embedding-based approaches.
  arXiv  Detail & Related papers  (2025-07-02T00:36:27Z)
• AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction [56.797874973414636]
  AnnoCaseLaw is a first-of-its-kind dataset of 471 meticulously annotated U.S. Appeals Court negligence cases. Our dataset lays the groundwork for more human-aligned, explainable Legal Judgment Prediction models. Results demonstrate that LJP remains a formidable task, with application of legal precedent proving particularly difficult.
  arXiv  Detail & Related papers  (2025-02-28T19:14:48Z)
• JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning [25.87736103281699]
  Four-Element Theory is a fundamental framework in criminal law, defining the constitution of crime through four dimensions. Many Large Language Models (LLMs) attempt to incorporate this theory when handling legal tasks. We introduce JUREX-4E, an expert-annotated knowledge base covering 155 criminal charges.
  arXiv  Detail & Related papers  (2025-02-24T14:02:00Z)
• Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios [0.0]
  GPT-4 consistently aligns more closely with progressive interpretations of the Constitution. Our experiments reveal a distinct tendency of GPT-4 to favor progressive legal interpretations.
  arXiv  Detail & Related papers  (2024-07-29T07:51:43Z)
• LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain [47.001169623840354]
  We aggregate 58 annotated legal datasets and write instructions for each, creating LawInstruct. LawInstruct covers 17 global jurisdictions, 24 languages and a total of 12M examples across diverse tasks such as legal QA, summarization of court cases, and legal argument mining. We find that legal-specific instruction tuning on Flan-T5 - yielding FLawN-T5 - improves performance on LegalBench across all model sizes.
  arXiv  Detail & Related papers  (2024-04-02T17:33:34Z)
• DELTA: Pre-train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment [55.91429725404988]
  We introduce DELTA, a discriminative model designed for legal case retrieval. We leverage shallow decoders to create information bottlenecks, aiming to enhance the representation ability. Our approach can outperform existing state-of-the-art methods in legal case retrieval.
  arXiv  Detail & Related papers  (2024-03-27T10:40:14Z)
• Towards Explainability in Legal Outcome Prediction Models [64.00172507827499]
  We argue that precedent is a natural way of facilitating explainability for legal NLP models. By developing a taxonomy of legal precedent, we are able to compare human judges and neural models. We find that while the models learn to predict outcomes reasonably well, their use of precedent is unlike that of human judges.
  arXiv  Detail & Related papers  (2024-03-25T15:15:41Z)
• Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration [52.57055162778548]
  Legal Judgment Prediction (LJP) has become an increasingly crucial task in Legal AI. Precedents are the previous legal cases with similar facts, which are the basis for the judgment of the subsequent case in national legal systems. Recent advances in deep learning have enabled a variety of techniques to be used to solve the LJP task.
  arXiv  Detail & Related papers  (2023-10-13T16:47:20Z)
• Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction [0.6091702876917281]
  Legal syllogism prompting (LoT) is a simple prompting method to teach large language models for legal judgment prediction. LoT teaches only that in the legal syllogism the major premise is law, the minor premise is the fact, and the conclusion is judgment. Our results show that LLMs with LoT achieve better performance than the baseline and chain of thought prompting.
  arXiv  Detail & Related papers  (2023-07-17T08:38:46Z)
• Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts [0.0]
  We evaluate the capability of a state-of-the-art generative pre-trained transformer (GPT) model to perform semantic annotation of short text snippets. We found that the GPT model performs surprisingly well in zero-shot settings on diverse types of documents.
  arXiv  Detail & Related papers  (2023-05-08T01:55:53Z)
• SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval [75.05173891207214]
  Legal case retrieval plays a core role in the intelligent legal system. Most existing language models have difficulty understanding the long-distance dependencies between different structures. We propose a new Structure-Aware pre-traIned language model for LEgal case Retrieval.
  arXiv  Detail & Related papers  (2023-04-22T10:47:01Z)
• Exploiting Contrastive Learning and Numerical Evidence for Confusing Legal Judgment Prediction [46.71918729837462]
  Given the fact description text of a legal case, legal judgment prediction aims to predict the case's charge, law article and penalty term. Previous studies fail to distinguish different classification errors with a standard cross-entropy classification loss. We propose a moco-based supervised contrastive learning to learn distinguishable representations. We further enhance the representation of the fact description with extracted crime amounts which are encoded by a pre-trained numeracy model.
  arXiv  Detail & Related papers  (2022-11-15T15:53:56Z)
• Factoring Statutory Reasoning as Language Understanding Challenges [48.13180364616141]
  We decompose statutory reasoning into four types of language-understanding challenge problems. We introduce concepts and structure found in Prolog programs. Models for statutory reasoning are shown to benefit from the additional structure.
  arXiv  Detail & Related papers  (2021-05-17T14:33:02Z)
• A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering [37.66486350122862]
  This paper investigates the performance of natural language understanding approaches on statutory reasoning. We introduce a dataset, together with a legal-domain text corpus. We contrast this with a hand-constructed Prolog-based system, designed to fully solve the task.
  arXiv  Detail & Related papers  (2020-05-11T16:54:42Z)
• Distinguish Confusing Law Articles for Legal Judgment Prediction [30.083642130015317]
  Legal Judgment Prediction (LJP) is the task of automatically predicting a law case's judgment results given a text describing its facts. We present an end-to-end model, LADAN, to solve the task of LJP.
  arXiv  Detail & Related papers  (2020-04-06T11:09:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.