KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#typescript #ai-agents #cli #open-source #ai #claude-code #codex #developer-tools #react #windows #deepseek-harness #ai-agent

LLM-and-Law

★ 325 Open GitHub ↗

This repository is dedicated to summarizing papers related to large language models with the field of law

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# LLM-and-Law
[![Awesome](https://awesome.re/badge.svg)](https://github.com/zjunlp/ModelEditingPapers) 
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
![](https://img.shields.io/github/last-commit/Jeryi-Sun/LLM-and-Law?color=green) 
![](https://img.shields.io/badge/PRs-Welcome-red)

This repository tracks papers and resources about large language models (LLMs) in the legal domain.

> Daily update 2026-08-14 (cs.CL): scanned 101 papers (date=2026-08-14), 4 new papers met the strict "legal task + LLM semantics" inclusion rule.
>
> Category increments today — Applications +2, Legal Reasoning Models +0, Legal Agent +1, Legal Problems +3, Data Resources +0, Law LLMs +0, Evaluation +3.

## Contents
- [Applications of Large Language Models in Legal Tasks](#applications-of-large-language-models-in-legal-tasks)
- [Legal Reasoning Models](#legal-reasoning-models)
- [Legal Agent](#legal-agent)
- [Legal Problems of Large Language Models](#legal-problems-of-large-language-models)
- [Data Resources for Large Language Models in Law](#data-resources-for-large-language-models-in-law)
- [Law LLMs](#law-llms)
- [Evaluation](#evaluation)

## Applications of Large Language Models in Legal Tasks

- On Measuring Semantic Preservation in Legal Ontology Learning [paper](https://papers.cool/arxiv/2608.12326)
- Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance [paper](https://papers.cool/arxiv/2608.12323)
- Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching [paper](https://papers.cool/arxiv/2608.11030)
- Evaluating Rational Contracting in Natural Language [paper](https://papers.cool/arxiv/2608.10475)
- Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law [paper](https://papers.cool/arxiv/2608.09393)
- PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs [paper](https://papers.cool/arxiv/2608.09028)
- ANNOTARES: A Dataset for Extracting Logical Structures from German Statutory Texts [paper](https://papers.cool/arxiv/2608.03898)
- CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models [paper](https://papers.cool/arxiv/2608.01292)
- Semantics of Subterfuge: Benchmarking Legal Deception Detection Against General-domain State-of-the-Art [paper](https://papers.cool/arxiv/2607.29066)
- Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning? [paper](https://papers.cool/arxiv/2607.26952)
- From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance [paper](https://papers.cool/arxiv/2607.24791)
- Legal Prompt Engineering for Multilingual Legal Judgement Prediction
- Can GPT-3 Perform Statutory Reasoning?
- Legal Prompting: Teaching a Language Model to Think Like a Lawyer
- Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards
- ChatGPT Goes to Law School
- ChatGPT, Professor of Law
- ChatGPT & Generative AI Systems as Quasi-Expert Legal Advice Lawyers - Case Study Considering Potential Appeal Against Conviction of Tom Hayes
- ‘Words Are Flowing Out Like Endless Rain Into a Paper Cup’: ChatGPT & Law School Assessments
- ChatGPT by OpenAI: The End of Litigation Lawyers?
- Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans
- ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark [paper](https://arxiv.org/pdf/2304.12202v1.pdf)
- How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization? [paper](https://arxiv.org/pdf/2306.01248v1.pdf)
- Explaining Legal Concepts with Augmented Large Language Models (GPT-4) [paper](https://arxiv.org/pdf/2306.09525v1.pdf)
- Garbage in, garbage out: Zero-shot detection of crime using Large Language Models [paper](http://arxiv.org/pdf/2307.06844v1)
- Legal Summarisation through LLMs: The PRODIGIT Project [paper](https://arxiv.org/pdf/2308.04416v1.pdf)
- Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task [paper](https://arxiv.org/pdf/2309.05501v1.pdf)
- PolicyGPT: Automated Analysis of Privacy Policies with Large Language Models
- Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise [paper](https://browse.arxiv.org/pdf/2310.03328v1.pdf)
- Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration [paper](https://arxiv.org/pdf/2310.09241.pdf)
- From Text to Structure: Using Large Language Models to Support the Development of Legal Expert Systems [paper](http://arxiv.org/pdf/2311.04911v1)
- Boosting legal case retrieval by query content selection with large language models [paper](https://arxiv.org/pdf/2312.03494v1.pdf)
- LLMediator: GPT-4 Assisted Online Dispute Resolution [paper](https://arxiv.org/pdf/2307.16732v1.pdf)
- Employing Label Models on ChatGPT Answers Improves Legal Text Entailment Performance [paper](https://arxiv.org/pdf/2401.17897v1.pdf)
- LLaMandement: Large Language Models for Summarization of French Legislative Proposals [paper](https://arxiv.org/pdf/2401.16182v1.pdf)
- **Logic Rules as Explanations for Legal Case Retrieval** [paper](http://arxiv.org/pdf/2403.01457v1) Our new paper, welcome to pay attention !!!
- Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models [paper](https://arxiv.org/pdf/2403.18093v1.pdf)
- BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models [paper](https://arxiv.org/abs/2403.18365)
- A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law [paper](https://arxiv.org/pdf/2405.01769v1#page=22.45)
- Archimedes-AUEB at SemEval-2024 Task 5: LLM explains Civil Procedure [paper](http://arxiv.org/pdf/2405.08502v1)
- More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs [paper](https://arxiv.org/pdf/2405.17830v1)
- Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model [paper](http://arxiv.org/pdf/2406.04202v1)
- Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning [paper](http://arxiv.org/pdf/2406.03600v1)
- GOLDCOIN: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory [paper](https://arxiv.org/pdf/2406.11149)
- Enabling Discriminative Reasoning in Large Language Models for Legal Judgment Prediction [paper](https://arxiv.org/abs/2407.01964)
- Large Language Models for Judicial Entity Extraction: A Comparative Study [paper](https://arxiv.org/abs/2407.05786)
- Applicability of Large Language Models and Generative Models for Legal Case Judgement Summarization [paper](https://arxiv.org/abs/2407.12848)
- LawLLM: Law Large Language Model for the US Legal System [paper](https://arxiv.org/pdf/2407.21065)
- Legal syllogism prompting: Teaching large language models for legal judgment prediction [paper](https://arxiv.org/pdf/2307.08321)
- Optimizing Numerical Estimation and Operational Efficiency in the Legal Domain through Large Language Models [paper](https://arxiv.org/pdf/2407.19041)
- Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools [paper](https://arxiv.org/pdf/2405.20362)
- KRAG Framework for Enhancing LLMs in the Legal Domain [paper](https://arxiv.org/abs/2410.07551)
- Legal Evaluations and Challenges of Large Language Models [paper](https://arxiv.org/abs/2411.10137)
- Analyzing Images of Legal Documents: Toward Multi-Modal LLMs for Access to Justice [paper](https://arxiv.org/pdf/2412.15260)
- Automating Legal Concept Interpretation with LLMs: Retrieval, Generation, and Evaluation [paper](https://arxiv.org/abs/2501.01743)
- Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains [paper](https://arxiv.org/abs/2501.14431)
- RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity [paper](https://arxiv.org/abs/2501.14113)
- Courtroom-LLM: A Legal-Inspired Multi-LLM Framework for Resolving Ambiguous Text Classifications [paper](https://aclanthology.org/2025.coling-main.493.pdf)
- LegalViz: Legal Text Visualization by Text To Diagram Generation [paper](https://arxiv.org/abs/2502.06147)
- Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning [paper](https://arxiv.org/abs/2502.05675)
- Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning [paper](https://arxiv.org/pdf/2502.07912)
- JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System [paper](https://arxiv.org/abs/2503.14258)
- LARGE: Legal Retrieval Augmented Generation Evaluation Tool [paper](https://arxiv.org/abs/2504.01698)
- Tasks and Roles in Legal AI: Data Curation, Annotation, and Verification [paper](https://arxiv.org/abs/2504.01349)
- The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting [paper](https://arxiv.org/abs/2505.12837)
- Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech [paper](https://arxiv.org/abs/2506.03009)
- CORE-KG: An LLM-Driven Knowledge Graph Construction Framework for Human Smuggling Networks [paper](https://arxiv.org/abs/2506.21607)
- LLM-based Embedders for Prior Case Retrieval [paper](https://arxiv.org/abs/2507.18455)
- Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models [paper](https://arxiv.org/abs/2507.16642)
- Using Large Language Models for Legal Decision-Making in Austrian Value-Added Tax Law: An Experimental Study [paper](https://arxiv.org/abs/2507.08468)
- ASVRI-Legal: Fine-Tuning LLMs with Retrieval Augmented Generation for Enhanced Legal Regulation [paper](https://arxiv.org/abs/2511.03563)
- LLMs in Interpreting Legal Documents [paper](https://arxiv.org/abs/2512.09830)
- HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment [paper](https://arxiv.org/abs/2512.01659)
- Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics [paper](https://arxiv.org/abs/2512.01020)
- Jurisdiction as Structural Barrier: How Privacy Policy Organization May Reduce Visibility of Substantive Disclosures [paper](https://papers.cool/arxiv/2601.20792)
- Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry [paper](https://papers.cool/arxiv/2602.04206)
- Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model [paper](https://papers.cool/arxiv/2602.07120)
- Synthesizing the Virtual Advocate: A Multi-Persona Speech Generation Framework for Diverse Linguistic Jurisdictions in Indic Languages [paper](https://papers.cool/arxiv/2602.11172)
- AI-Assisted Moot Courts: Simulating Justice-Specific Questioning in Oral Arguments [paper](https://papers.cool/arxiv/2603.04718)
- LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction [paper](https://papers.cool/arxiv/2603.11446)
- De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules [paper](https://papers.cool/arxiv/2604.02276)
- ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance [paper](https://papers.cool/arxiv/2604.12308)
- Eskwai for Students: Generative AI Assistant for Legal Education in Ghana [paper](https://papers.cool/arxiv/2605.15380)
- Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization [paper](https://papers.cool/arxiv/2605.17379)
- Exploring Lightweight Large Language Models for Court View Generation [paper](https://papers.cool/arxiv/2605.16770)
- Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free [paper](https://papers.cool/arxiv/2605.16767)
- Chunking German Legal Code [paper](https://papers.cool/arxiv/2605.19806)
- Generating Legal Commentaries from Case Databases via Retrieval, Clustering, and Generation [paper](https://papers.cool/arxiv/2605.24534)
- Decompose-and-Refine: Structured Legal Question Answering with Parametric Retrieval [paper](https://papers.cool/arxiv/2605.24454)
- Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service [paper](https://papers.cool/arxiv/2605.26019)
- Traceable by Design: An LLM Pipeline and Dashboard for EU Regulatory Consultation Analysis [paper](https://papers.cool/arxiv/2605.30995)
- ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law [paper](https://papers.cool/arxiv/2605.30589)
- Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs [paper](https://papers.cool/arxiv/2606.00898)
- Enhancing BiGRU with a KAN Block for Legal Document Classification and Summarization [paper](https://papers.cool/arxiv/2606.00116)
- On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral [paper](https://papers.cool/arxiv/2606.00272)
- Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA [paper](https://papers.cool/arxiv/2606.03728)
- EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction [paper](https://papers.cool/arxiv/2606.02971)
- DAR: Deontic Reasoning with Agentic Harnesses [paper](https://papers.cool/arxiv/2606.05009)
- GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation [paper](https://papers.cool/arxiv/2606.05002)
- Civil Court Simulation with Large Language Models [paper](https://papers.cool/arxiv/2606.09632)
- LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks [paper](https://papers.cool/arxiv/2606.09389)
- From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing [paper](https://papers.cool/arxiv/2606.08932)
- Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering [paper](https://papers.cool/arxiv/2606.07523)
- FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs [paper](https://papers.cool/arxiv/2606.19710)
- Reinforcement learning to improve large language model-based automated code compliance systems [paper](https://papers.cool/arxiv/2606.22402)
- Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts [paper](https://papers.cool/arxiv/2606.23375)
- Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification [paper](https://papers.cool/arxiv/2606.20929)

- A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs [paper](https://papers.cool/arxiv/2606.28044)
- PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation [paper](https://papers.cool/arxiv/2607.09094)
- Cross-Architecture LLM Ensembles, Feature-Based Reranking and Retrieval-Augmented Prompting for Legal Information Processing [paper](https://papers.cool/arxiv/2607.11400)
- When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation [paper](https://papers.cool/arxiv/2607.10480)
- The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation [paper](https://papers.cool/arxiv/2607.19226)
- Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning [paper](https://papers.cool/arxiv/2607.19181)
- AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System [paper](https://papers.cool/arxiv/2607.18825)
- Enabling Multilingual Privacy Policy Audits: Large-Scale Analysis of Spanish Mobile Apps [paper](https://papers.cool/arxiv/2607.18424)
- From Obligation to Specification: A Survey on Validating EU AI Act Requirements in RE [paper](https://papers.cool/arxiv/2607.21608)
- Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Management [paper](https://papers.cool/arxiv/2607.24352)
- Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh [paper](https://papers.cool/arxiv/2607.23446)

## Legal Reasoning Models

- LexPro-1.0 Technical Report [paper](https://arxiv.org/pdf/2503.06949)
- LexPam: Legal Procedure Awareness-Guided Mathematical Reasoning [paper](https://arxiv.org/pdf/2504.02590)
- Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning [paper](https://arxiv.org/abs/2505.10182)
- SyLeR: A Framework for Explicit Syllogistic Legal Reasoning in Large Language Models [paper](https://arxiv.org/pdf/2504.04042)
- Contractual Deepfakes: Can Large Language Models Generate Contracts? [paper](https://papers.cool/arxiv/2602.09384)
- LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues [paper](https://papers.cool/arxiv/2604.19464)
- Falkor-IRAC: Graph-Constrained Generation for Verified Legal Reasoning in Indian Judicial AI [paper](https://papers.cool/arxiv/2605.14665)
- Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning [paper](https://papers.cool/arxiv/2605.14049)
- TypedCSIP: Typed Counterfactual Pretraining for Chinese Legislative Conflict Classification [paper](https://papers.cool/arxiv/2605.25474)
- By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They Encode [paper](https://papers.cool/arxiv/2605.25186)
- Scaling Multi-Hop Training Data via Graph-Constrained Path Selection [paper](https://papers.cool/arxiv/2605.31238)
- DAR: Deontic Reasoning with Agentic Harnesses [paper](https://papers.cool/arxiv/2606.05009)
- Civil Court Simulation with Large Language Models [paper](https://papers.cool/arxiv/2606.09632)
- From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing [paper](https://papers.cool/arxiv/2606.08932)
- Generative Chinese Statute Retrieval [paper](https://papers.cool/arxiv/2607.11109)
- Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh [paper](https://papers.cool/arxiv/2607.23446)
- Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation [paper](https://papers.cool/arxiv/2607.27783)

## Legal Agent

- Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance [paper](https://papers.cool/arxiv/2608.12323)
- Evaluating Rational Contracting in Natural Language [paper](https://papers.cool/arxiv/2608.10475)
- PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs [paper](https://papers.cool/arxiv/2608.09028)
- From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance [paper](https://papers.cool/arxiv/2607.24791)
- When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models [paper](https://arxiv.org/abs/2605.02363)
- Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication [paper](https://arxiv.org/abs/2605.02472)
- SimuCourt: Building Judicial Decision-Making Agents with Real-world Judgement Documents [paper](https://arxiv.org/pdf/2403.02959v1.pdf)
- Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration [paper](https://arxiv.org/abs/2410.02507)
- Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction [paper](https://arxiv.org/abs/2502.06882)
- CLAIM: An Intent-Driven Multi-Agent Framework for Analyzing Manipulation in Courtroom Dialogues [paper](https://arxiv.org/abs/2506.04131)
- PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements [paper](https://arxiv.org/abs/2506.00608)
- LLM Agents in Law: Taxonomy, Applications, and Challenges [paper](https://arxiv.org/pdf/2601.06216)
- Dissecting Judicial Reasoning in U.S. Copyright Damage Awards [paper](https://papers.cool/arxiv/2601.09459)
- Multimodal Multi-Agent Empowered Legal Judgment Prediction [paper](https://papers.cool/arxiv/2601.12815)
- LegalMALR:Multi-Agent Query Understanding and LLM-Based Reranking for Chinese Statute Retrieval [paper](https://papers.cool/arxiv/2601.17692)
- LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [paper](https://papers.cool/arxiv/2602.00642)
- Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India [paper](https://papers.cool/arxiv/2602.23371)
- LexChronos: An Agentic Framework for Structured Event Timeline Extraction in Indian Jurisprudence [paper](https://papers.cool/arxiv/2603.01651)
- Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA [paper](https://papers.cool/arxiv/2603.08501)
- Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents [paper](https://papers.cool/arxiv/2605.14057)
- Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning [paper](https://papers.cool/arxiv/2605.25920)
- SIA: Self Improving AI with Harness & Weight Updates [paper](https://papers.cool/arxiv/2605.27276)
- LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning [paper](https://papers.cool/arxiv/2605.28120)
- DAR: Deontic Reasoning with Agentic Harnesses [paper](https://papers.cool/arxiv/2606.05009)
- GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation [paper](https://papers.cool/arxiv/2606.05002)
- Civil Court Simulation with Large Language Models [paper](https://papers.cool/arxiv/2606.09632)
- From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing [paper](https://papers.cool/arxiv/2606.08932)
- DeXposure-Claw: An Agentic System for DeFi Risk Supervision [paper](https://papers.cool/arxiv/2606.19501)
- Agentic Evaluation of Copyright Law Compliance [paper](https://papers.cool/arxiv/2607.21799)
- From Obligation to Specification: A Survey on Validating EU AI Act Requirements in RE [paper](https://papers.cool/arxiv/2607.21608)

## Legal Problems of Large Language Models

- Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance [paper](https://papers.cool/arxiv/2608.12323)
- Is this Citation on Point? [paper](https://papers.cool/arxiv/2608.12571)
- SoK: From Generation to Consumption of Privacy Documents in Software Systems [paper](https://papers.cool/arxiv/2608.12511)
- Evaluating Rational Contracting in Natural Language [paper](https://papers.cool/arxiv/2608.10475)
- Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law [paper](https://papers.cool/arxiv/2608.09393)
- LexKairos: Benchmarking Legal Temporal Capabilities in LLMs [paper](https://papers.cool/arxiv/2608.09106)
- Knowing the Form, Not the Function: Automatically Auditing Answer--Authority Decoupling in Legal Benchmarks [paper](https://papers.cool/arxiv/2608.02621)
- CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models [paper](https://papers.cool/arxiv/2608.01292)
- Semantics of Subterfuge: Benchmarking Legal Deception Detection Against General-domain State-of-the-Art [paper](https://papers.cool/arxiv/2607.29066)
- Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models
- Persistent Anti-Muslim Bias in Large Language Models
- Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
- The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination
- The GPTJudge: Justice in a Generative AI World [paper](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4460184)
- Is the U.S. Legal System Ready for AI's Challenges to Human Values? [paper](http://arxiv.org/pdf/2308.15906v1)
- Questioning Biases in Case Judgment Summaries: Legal Datasets or Large Language Models? [paper](https://arxiv.org/pdf/2312.00554.pdf)
- Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
- A Legal Framework for Natural Language Processing Model Training in Portugal [paper](http://arxiv.org/pdf/2405.00536v1)
- LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain [paper](https://arxiv.org/abs/2408.10343)
- Bias in Large Language Models: Origin, Evaluation, and Mitigation [paper](https://arxiv.org/abs/2411.10915)
- An Information Theoretic Approach to Operationalize Right to Data Protection [paper](https://arxiv.org/abs/2411.08506)
- Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench [paper](https://arxiv.org/abs/2410.22108)
- Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance [paper](https://arxiv.org/abs/2503.04736)
- TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law [paper](https://arxiv.org/pdf/2507.21134)
- Large Language Models as Search Engines: Societal Challenges [paper](https://arxiv.org/abs/2512.08946)
- From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models [paper](https://papers.cool/arxiv/2603.04828)
- TimeMark: A Trustworthy Time Watermarking Framework for Exact Generation-Time Recovery from AIGC [paper](https://papers.cool/arxiv/2604.12216)
- To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model [paper](https://papers.cool/arxiv/2605.14291)
- Divergence Decoding: Inference-Time Unlearning via Auxiliary Models [paper](https://papers.cool/arxiv/2605.31293)
- Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs [paper](https://papers.cool/arxiv/2606.00898)
- Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs [paper](https://papers.cool/arxiv/2606.00333)
- Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts [paper](https://papers.cool/arxiv/2606.23375)
- Who Checks the Citations? Benchmarking Legal Hallucination Detection [paper](https://papers.cool/arxiv/2606.21155)
- Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification [paper](https://papers.cool/arxiv/2606.20929)

- Position: The Term "Machine Unlearning" Is Overused in LLMs [paper](https://papers.cool/arxiv/2606.27379)
- Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages [paper](https://papers.cool/arxiv/2606.28867)
- Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law [paper](https://papers.cool/arxiv/2606.31250)
- The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI [paper](https://papers.cool/arxiv/2607.13044)
- Agentic Evaluation of Copyright Law Compliance [paper](https://papers.cool/arxiv/2607.21799)

## Data Resources for Large Language Models in Law

- Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law [paper](https://papers.cool/arxiv/2608.09393)
- LexKairos: Benchmarking Legal Temporal Capabilities in LLMs [paper](https://papers.cool/arxiv/2608.09106)
- ANNOTARES: A Dataset for Extracting Logical Structures from German Statutory Texts [paper](https://papers.cool/arxiv/2608.03898)
- CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models [paper](https://papers.cool/arxiv/2608.01292)
- Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning? [paper](https://papers.cool/arxiv/2607.26952)
- CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
- When does pretraining help? assessing self-supervised learning for law and the casehold dataset of 53,000+ legal holdings
- LeCaRD: a legal case retrieval dataset for Chinese law system
- LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development
- Legal Extractive Summarization of U.S. Court Opinions
- Awesome Chinese Legal Resources [github](https://github.com/pengxiao-song/awesome-chinese-legal-resources)
- MultiLegalPile: A 689GB Multilingual Legal Corpus [paper](https://arxiv.org/pdf/2306.02069v1.pdf)
- The Cambridge Law Corpus: A Corpus for Legal AI Research
- TransformLLM: Adapting Large Language Models via LLM-Transformed Reading Comprehension Text [paper](https://arxiv.org/abs/2410.21479)
- Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges [paper](https://arxiv.org/abs/2410.21306)
- ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models [paper](https://arxiv.org/abs/2410.18491)
- Augmenting Legal Decision Support Systems with LLM-based NLI for Analyzing Social Media Evidence [paper](https://arxiv.org/abs/2410.15990)
- CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions [paper](https://arxiv.org/abs/2501.00097)
- From Answers to Guidance: A Proactive Dialogue System for Legal Documents [paper](https://papers.cool/arxiv/2510.19723)
- A Greek Government Decisions Dataset for Public-Sector Analysis and Insight [paper](https://arxiv.org/abs/2512.05647
- Data Augmented Pipeline for Legal Information Extraction and Reasoning [paper](https://papers.cool/arxiv/2601.05609)
- Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law [paper](https://papers.cool/arxiv/2601.14160)
- Knowledge Augmented Entity and Relation Extraction for Legal Documents with Hypergraph Neural Network [paper](https://papers.cool/arxiv/2602.08289)
- Quecto-V1: Empirical Analysis of 8-bit Quantized Small Language Models for On-Device Legal Retrieval [paper](https://papers.cool/arxiv/2602.16640)
- SinhaLegal: A Benchmark Corpus for Information Extraction and Analysis in Sinhala Legislative Texts [paper](https://papers.cool/arxiv/2603.04854)
- LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMs [paper](https://papers.cool/arxiv/2603.08286)
- RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian [paper](https://papers.cool/arxiv/2604.19593)
- Automatic Construction of a Legal Citation Graph from 100 Million Ukrainian Court Decisions: Large-Scale Extraction, Topological Analysis, and Ontology-Driven Clustering [paper](https://papers.cool/arxiv/2605.15362)
- Temporal Decay of Co-Citation Predictability: A 20-Year Statute Retrieval Benchmark from 396M Ukrainian Court Citations [paper](https://papers.cool/arxiv/2605.17639)
- IMLJD: A Computational Dataset for Indian Matrimonial Litigation Analysis [paper](https://papers.cool/arxiv/2605.19346)
- Fine-grained Claim-level RAG Benchmark for Law [paper](https://papers.cool/arxiv/2605.21071)
- A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text [paper](https://papers.cool/arxiv/2605.22978)
- Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions [paper](https://papers.cool/arxiv/2605.24452)
- Bundesrecht: An Open Library and Corpus for German Statutory Reference Processing [paper](https://papers.cool/arxiv/2605.31338)
- CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law [paper](https://papers.cool/arxiv/2605.30497)
- Scaling Multi-Hop Training Data via Graph-Constrained Path Selection [paper](https://papers.cool/arxiv/2605.31238)
- ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law [paper](https://papers.cool/arxiv/2605.30589)
- Citation Grounding: Detecting and Reducing LLM Citation Hallucinations via Legal Citation Graphs [paper](https://papers.cool/arxiv/2606.00898)
- Enhancing BiGRU with a KAN Block for Legal Document Classification and Summarization [paper](https://papers.cool/arxiv/2606.00116)
- Digging Up Citations: FOSSIL, a Dataset and Workflow for Reference Extraction in Law and the Humanities [paper](https://papers.cool/arxiv/2606.01109)
- EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction [paper](https://papers.cool/arxiv/2606.02971)
- HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule [paper](https://papers.cool/arxiv/2606.06679)
- LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks [paper](https://papers.cool/arxiv/2606.09389)
- From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing [paper](https://papers.cool/arxiv/2606.08932)
- Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering [paper](https://papers.cool/arxiv/2606.07523)
- REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection [paper](https://papers.cool/arxiv/2606.19881)
- FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs [paper](https://papers.cool/arxiv/2606.19710)
- Who Checks the Citations? Benchmarking Legal Hallucination Detection [paper](https://papers.cool/arxiv/2606.21155)
- Open but Incompatible: A License Compatibility Analysis of Corpora for Low-Resource African Languages [paper](https://papers.cool/arxiv/2606.28867)
- Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy [paper](https://papers.cool/arxiv/2607.08346)
- Enabling Multilingual Privacy Policy Audits: Large-Scale Analysis of Spanish Mobile Apps [paper](https://papers.cool/arxiv/2607.18424)
- Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh [paper](https://papers.cool/arxiv/2607.23446)

## Law LLMs

- LawGPT_zh [github](https://github.com/LiuHC0428/LAW-GPT)
- LaWGPT [github](https://github.com/pengxiao-song/LaWGPT)
- Lawyer LLaMA [github](https://github.com/AndrewZhe/lawyer-llama)
- LexiLaw [github](https://github.com/CSHaitao/LexiLaw)
- LexGPT 0.1: pre-trained GPT-J models with Pile of Law [paper](https://arxiv.org/pdf/2306.05431v1.pdf)
- TOWARDS THE EXPLOITATION OF LLM-BASED CHATBOT FOR PROVIDING LEGAL SUPPORT TO PALESTINIAN COOPERATIVES [paper](https://arxiv.org/pdf/2306.05827v1.pdf)
- ChatLaw: Open-Source Legal Large Language Model with Integrated External Knowledge Bases [paper](http://arxiv.org/pdf/2306.16092v1)
- DISC-LawLLM [github](https://github.com/FudanDISC/DISC-LawLLM)
- InternLM-Law: An Open Source Chinese Legal Large Language Model [paper](https://arxiv.org/pdf/2406.14887v1)
- SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain [paper](https://arxiv.org/pdf/2407.19584)
- LAWGPT: KNOWLEDGE-GUIDED DATA GENERATION AND ITS APPLICATION TO LEGAL LLM [paper](https://arxiv.org/pdf/2502.06572)
- HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong [paper](https://arxiv.org/abs/2507.11502)
- HUKUKBERT: Domain-Specific Language Model for Turkish Law [paper](https://papers.cool/arxiv/2604.04790)
- PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs [paper](https://arxiv.org/pdf/2604.17543)
- ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law [paper](https://papers.cool/arxiv/2605.30589)
- Legal Domain Adaptation of Modern BERT Models [paper](https://papers.cool/arxiv/2606.28538)
- Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh [paper](https://papers.cool/arxiv/2607.23446)

## Evaluation

- Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA [paper](https://papers.cool/arxiv/2606.03728)
- EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction [paper](https://papers.cool/arxiv/2606.02971)
- HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule [paper](https://papers.cool/arxiv/2606.06679)
- LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks [paper](https://papers.cool/arxiv/2606.09389)
- From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing [paper](https://papers.cool/arxiv/2606.08932)
- Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering [paper](https://papers.cool/arxiv/2606.07523)
- REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection [paper](https://papers.cool/arxiv/2606.19881)
- DeXposure-Claw: An Agentic System for DeFi Risk Supervision [paper](https://papers.cool/arxiv/2606.19501)

- Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts [paper](https://papers.cool/arxiv/2606.23375)
- Who Checks the Citations? Benchmarking Legal Hallucination Detection [paper](https://papers.cool/arxiv/2606.21155)
- Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification [paper](https://papers.cool/arxiv/2606.20929)
- Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law [paper](https://papers.cool/arxiv/2606.31250)

- Do LLMs Fabricate Legal Citations? A Bilingual Benchmark on Saudi Data Protection Law and the GDPR [paper](https://papers.cool/arxiv/2607.11127)
- The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI [paper](https://papers.cool/arxiv/2607.13044)

The survey paper is shown in [paper](https://arxiv.org/abs/2403.11152)

# Acknowledgement
Please cite the following papers as references if this repository helps you (*ゝω・)ﾉThanks!

```bib
@article{sun2023short,
  title={A short survey of viewing large language models in legal aspect},
  author={Sun, Zhongxiang},
  journal={arXiv preprint arXiv:2303.09136},
  year={2023}
}
```
- AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System [paper](https://papers.cool/arxiv/2607.18825)
- Enabling Multilingual Privacy Policy Audits: Large-Scale Analysis of Spanish Mobile Apps [paper](https://papers.cool/arxiv/2607.18424)
- Agentic Evaluation of Copyright Law Compliance [paper](https://papers.cool/arxiv/2607.21799)
- From Obligation to Specification: A Survey on Validating EU AI Act Requirements in RE [paper](https://papers.cool/arxiv/2607.21608)
- Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation [paper](https://papers.cool/arxiv/2607.27783)

LLM-and-Law

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README