This is the official repository of A Survey of Large Language Models for Legal Tasks: Progress, Prospects and Challenges.
Recent advances in large language models (LLMs) have unlocked new opportunities for machine learning and deep learning applications in the legal domain. These models have demonstrated remarkable capabilities in understanding complex legal language, analyzing lengthy documents, and generating contextually relevant legal text. In this survey, we explore the application of LLMs on various legal tasks, focusing on their potential to transform legal practice and drive innovation. We first categorize existing LLMs and their adaptations and provide an overview of their capabilities in legal reasoning, supporting decision-making, and democratizing legal services. We then organize the existing literature by key application areas, including legal case retrieval, legal document summarization, court judgment prediction, legal question-answering, legal agents, legal document drafting, and legal education. For each application area, we delve into specific methodologies, such as retrieval-augmented generation, prompting strategies, and chain-of-thought reasoning. Furthermore, a comprehensive collection of legal datasets, benchmarks, and model resources is presented as a practical reference for researchers and practitioners. Finally, we outline open challenges and future prospects, addressing issues such as bias, interpretability, data privacy, and regulatory compliance in legal AI. Our work provides a structured and practiceoriented overview to facilitate the adoption and further development of LLMs in the legal sector.
- [2025] [Journal] Automating construction contract review using knowledge graph-enhanced large language models Zheng et al. [paper]
- [2025] [Journal] Predicting potentially unfair clauses in Chilean terms of services with natural language processing Loeffler et al. [paper]
- [2025] [Journal] Auto-Drafting Police Reports from Noisy ASR Outputs: A Trust-Centered LLM Approach Kulkarni et al. [paper]
- [2025] [Journal] CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation Li et al. [paper]
- [2025] [Journal] Better Bill GPT: Comparing Large Language Models against Legal Invoice Reviewers Whitehouse et al. [paper]
- [2025] [Journal] Towards robust legal reasoning: Harnessing logical llms in law Kant et al. [paper]
- [2024] [Journal] Better call gpt, comparing large language models against lawyers Martin et al. [paper]
- [2024] [Journal] LegiLM: A Fine-Tuned Legal Language Model for Data Compliance Zhu et al. [paper]
- [2024] [Journal] Construction contract risk identification based on knowledge-augmented language models Wong et al. [paper]
- [2024] [Journal] Generating Clarification Questions for Disambiguating Contracts Singhal et al. [paper]
- [2024] [Conference] LLMs to the Rescue: Explaining DSA Statements of Reason with Platform`s Terms of Services Aspromonte et al. [paper]
- [2024] [Conference] Enhancing Contract Negotiations with LLM-Based Legal Document Comparison Narendra et al. [paper]
- [2024] [Conference] LexDrafter: Terminology Drafting for Legislative Documents Using Retrieval Augmented Generation Chouhan et al. [paper]
- [2024] [Conference] Dallma: Semi-structured legal reasoning and drafting with large language models Westermann et al. [paper]
- [2024] [Journal] Towards the LLM-Based Generation of Formal Specifications from Natural-Language Contracts: Early Experiments with Symboleo Nihad et al. [paper]
- [2024] [Journal] LegalLens: Leveraging LLMs for legal violation identification in unstructured text Bernsohn et al. [paper]
- [2023] [Conference] Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts Savelka et al. [paper]
- [2023] [Conference] Applying Large Language Models for Enhancing Contract Drafting Lam et al. [paper]
- [2025] [Conference] Courtroom-LLM: A Legal-Inspired Multi-LLM Framework for Resolving Ambiguous Text Classifications Jung et al. [paper]
- [2025] [Journal] Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction Yue et al. [paper]
- [2025] [Conference] Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction Chen et al. [paper]
- [2025] [Conference] LAW: Legal Agentic Workflows for Custody and Fund Services Contracts Watson et al. [paper]
- [2024] [Journal] Agentcourt: Simulating court with adversarial evolvable lawyer agents Chen et al. [paper]
- [2024] [Journal] Agents on the Bench: Large Language Model Based Multi Agent Framework for Trustworthy Digital Justice Jiang et al. [paper]
- [2024] [Journal] Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration Yuan et al. [paper]
- [2024] [Conference] LegalGPT: Legal Chain of Thought for the Legal Large Language Model Multi-agent Framework Shi et al. [paper]
- [2024] [Journal] Lawluo: A chinese law firm co-run by llm agents Sun et al. [paper]
- [2024] [Journal] Can we trust AI agents? An experimental study towards trustworthy LLM-based multi-agent systems for AI ethics de et al. [paper]
- [2024] [Conference] AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation He et al. [paper]
- [2024] [Journal] Simucourt: Building judicial decision-making agents with real-world judgement documents He et al. [paper]
- [2024] [Journal] Employing label models on ChatGPT answers improves legal text entailment performance Nguyen et al. [paper]
- [2024] [Conference] Logic Rules as Explanations for Legal Case Retrieval Sun et al. [paper]
- [2024] [Journal] Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models Nguyen et al. [paper]
- [2024] [Journal] Leveraging large language models for relevance judgments in legal case retrieval Ma et al. [paper]
- [2024] [Journal] Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation Deng et al. [paper]
- [2024] [Journal] Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval Trung et al. [paper]
- [2024] [Journal] Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval Nguyen et al. [paper]
- [2023] [Conference] Boosting legal case retrieval by query content selection with large language models Zhou et al. [paper]
- [2025] [Journal] A Llama walks into the'Bar': Efficient Supervised Fine-Tuning for Legal Reasoning in the Multi-state Bar Exam Fernandes et al. [paper]
- [2025] [Journal] Artificial Intelligence and Legal Analysis: Implications for Legal Education and the Profession Peoples et al. [paper]
- [2025] [Journal] Automating Legal Concept Interpretation with LLMs: Retrieval, Generation, and Evaluation Luo et al. [paper]
- [2024] [Journal] Gpt-4 passes the bar exam Katz et al. [paper]
- [2024] [Journal] Re-evaluating GPT-4’s bar exam performance Martínez et al. [paper]
- [2024] [Journal] The Other'LLM': Large Language Models and the Future of Legal Education Nelson et al. [paper]
- [2024] [Journal] Leveraging large language models for learning complex legal concepts through storytelling Jiang et al. [paper]
- [2023] [Journal] Chatgpt may pass the bar exam soon, but has a long way to go for the lexglue benchmark Chalkidis et al. [paper]
- [2023] [Journal] Explaining legal concepts with augmented large language models (gpt-4) Savelka et al. [paper]
- [2023] [Journal] 'Words Are Flowing out Like Endless Rain into a Paper Cup': ChatGPT & Law School Assessments Hargreaves et al. [paper]
- [2023] [Journal] ChatGPT and the future of legal education and practice Ajevski et al. [paper]
- [2023] [Journal] Chatgpt, professor of law Oltz et al. [paper]
- [2022] [Journal] Legal prompting: Teaching a language model to think like a lawyer Yu et al. [paper]
- [2022] [Journal] GPT takes the bar exam Bommarito et al. [paper]
- [2022] [Journal] Law informs code: A legal informatics approach to aligning artificial intelligence with humans Nay et al. [paper]
- [2021] [Journal] ChatGPT goes to law school Choi et al. [paper]
- [2025] [Journal] An LLMs-based neuro-symbolic legal judgment prediction framework for civil cases Wei et al. [paper]
- [2025] [Journal] Can Large Language Models Predict the Outcome of Judicial Decisions? Kmainasi et al. [paper]
- [2024] [Conference] Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction Deng et al. [paper]
- [2024] [Journal] Athena: Retrieval-augmented legal judgment prediction with large language models Peng et al. [paper]
- [2024] [Journal] Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning Zhang et al. [paper]
- [2024] [Conference] Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models Nigam et al. [paper]
- [2024] [Journal] Llm vs. lawyers: Identifying a subset of summary judgments in a large uk case law dataset Izzidien et al. [paper]
- [2024] [Journal] How do judges use large language models? Evidence from Shenzhen Liu et al. [paper]
- [2024] [Journal] Boosting court judgment prediction and explanation using legal entities Benedetto et al. [paper]
- [2024] [Conference] Explicitly Integrating Judgment Prediction with Legal Document Retrieval: A Law-Guided Generative Approach Qin et al. [paper]
- [2024] [Journal] LegalAsst: Human-centered and AI-empowered machine to enhance court productivity and legal assistance Han et al. [paper]
- [2024] [Conference] Unleashing the Power of LLMs in Court View Generation by Stimulating Internal Knowledge and Incorporating External Knowledge Liu et al. [paper]
- [2024] [Conference] Divide and Conquer: Legal Concept-guided Criminal Court View Generation Xu et al. [paper]
- [2024] [Conference] Comparative Study of Explainability Methods for Legal Outcome Prediction Staliunaite et al. [paper]
- [2024] [Conference] Rethinking the development of large language models from the causal perspective: a legal text prediction case study Chen et al. [paper]
- [2024] [Conference] Exploring large language models and hierarchical frameworks for classification of large unstructured legal documents Prasad et al. [paper]
- [2023] [Conference] Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration Wu et al. [paper]
- [2023] [Conference] Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction Jiang et al. [paper]
- [2023] [Journal] A comprehensive evaluation of large language models on legal judgment prediction Shui et al. [paper]
- [2023] [Conference] Syllogistic Reasoning for Legal Judgment Analysis Deng et al. [paper]
- [2023] [Conference] LLMs -- the Good, the Bad or the Indispensable?: A Use Case on Legal Statute Prediction and Legal Judgment Prediction on Indian Court Cases Vats et al. [paper]
- [2023] [Conference] Legal Judgment Prediction: If You Are Going to Do It, Do It Right Medvedeva et al. [paper]
- [2022] [Journal] Legal prompt engineering for multilingual legal judgement prediction Trautmann et al. [paper]
- [2025] [Conference] InternLM-Law: An Open-Sourced Chinese Legal Large Language Model Fei et al. [paper]
- [2025] [Journal] LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM Zhou et al. [paper]
- [2024] [Conference] LawLLM: Law large language model for the US legal system Shu et al. [paper]
- [2024] [Journal] Lawgpt: A chinese legal knowledge-enhanced large language model Zhou et al. [paper]
- [2024] [Journal] Internlm-law: An open source chinese legal large language model Fei et al. [paper]
- [2024] [Journal] Saullm-54b & saullm-141b: Scaling up domain adaptation for the legal domain Colombo et al. [paper]
- [2023] [Journal] Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain Zhang et al. [paper]
- [2023] [Journal] Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model Cui et al. [paper]
- [2023] [Conference] Legalbert-pt: A pretrained language model for the brazilian portuguese legal domain Silveira et al. [paper]
- [2023] [Conference] Pre-trained language models for the legal domain: a case study on Indian law Paul et al. [paper]
- [2023] [Journal] Lawyer llama technical report Huang et al. [paper]
- [2023] [Journal] LexGPT 0.1: pre-trained GPT-J models with Pile of Law Lee et al. [paper]
- [2023] [Journal] RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze! Pradeep et al. [paper]
- [2022] [Journal] AraLegal-BERT: A pretrained language model for Arabic Legal text Al-Qurishi et al. [paper]
- [2022] [Conference] Cross-domain analysis on Japanese legal pretrained language models Miyazaki et al. [paper]
- [2022] [Journal] Processing long legal documents with pre-trained transformers: Modding legalbert and longformer Mamakas et al. [paper]
- [2022] [Journal] LegalRelectra: Mixed-domain language modeling for long-range legal text comprehension Hua et al. [paper]
- [2021] [Journal] JuriBERT: A masked-language model adaptation for French legal text Douka et al. [paper]
- [2021] [Conference] jurbert: A romanian bert model for legal judgement prediction Masala et al. [paper]
- [2020] [Conference] LEGAL-BERT: The Muppets straight out of Law School Chalkidis et al. [paper]
- [2019] [Conference] Neural Legal Judgment Prediction in English Chalkidis et al. [paper]
- [2025] [Journal] Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering Hu et al. [paper]
- [2025] [Conference] A Reasoning-Focused Legal Retrieval Benchmark Zheng et al. [paper]
- [2025] [Conference] Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering Tao et al. [paper]
- [2025] [Journal] Intelligent Legal Assistant: An Interactive Clarification System for Legal Question Answering Yao et al. [paper]
- [2025] [Journal] Top 2 at ALQAC 2024: Large Language Models (LLMs) for Legal Question Answering Pham et al. [paper]
- [2025] [Journal] NitiBench: A Comprehensive Study of LLM Framework Capabilities for Thai Legal Question Answering Akarajaradwong et al. [paper]
- [2025] [Journal] SyLeR: A Framework for Explicit Syllogistic Legal Reasoning in Large Language Models Zhang et al. [paper]
- [2024] [Journal] ITALIAN-LEGAL-BERT models for improving natural language processing tasks in the Italian legal domain Licari et al. [paper]
- [2024] [Conference] EuropeanLawAdvisor: an open source search engine for European laws Russo et al. [paper]
- [2024] [Conference] Attributed Question Answering for Preconditions in the Dutch Law Redelaar et al. [paper]
- [2024] [Conference] DeliLaw: A Chinese Legal Counselling System Based on a Large Language Model Xie et al. [paper]
- [2024] [Conference] Reasoning before Responding: Towards Legal Long-form Question Answering with Interpretability Ujwal et al. [paper]
- [2024] [Conference] Cross Examine: An Ensemble-based approach to leverage Large Language Models for Legal Text Analytics Chowdhury et al. [paper]
- [2024] [Journal] Answering Questions in Stages: Prompt Chaining for Contract QA Roegiest et al. [paper]
- [2024] [Conference] ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice Hu et al. [paper]
- [2024] [Conference] Measuring the Groundedness of Legal Question-Answering Systems Trautmann et al. [paper]
- [2023] [Journal] Chatgpt & generative ai systems as quasi-expert legal advice lawyers-case study considering potential appeal against conviction of tom hayes Macey-Dare et al. [paper]
- [2023] [Conference] Questions about Contracts: Prompt Templates for Structured Answer Generation Roegiest et al. [paper]
- [2023] [Conference] Retrieval-based evaluation for LLMs: a case study in Korean legal QA Ryu et al. [paper]
- [2025] [Journal] ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting Wang et al. [paper]
- [2025] [Conference] LAiW: A Chinese Legal Large Language Models Benchmark Dai et al. [paper]
- [2025] [Journal] SwiLTra-Bench: The Swiss Legal Translation Benchmark Niklaus et al. [paper]
- [2025] [Journal] JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System Su et al. [paper]
- [2025] [Journal] LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation Li et al. [paper]
- [2025] [Journal] LegalBench. PT: A Benchmark for Portuguese Law Canaverde et al. [paper]
- [2024] [Conference] AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts Braun et al. [paper]
- [2024] [Conference] LawBench: Benchmarking Legal Knowledge of Large Language Models Fei et al. [paper]
- [2024] [Conference] LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models Li et al. [paper]
- [2024] [Journal] LegalAgentBench: Evaluating LLM Agents in Legal Domain Li et al. [paper]
- [2024] [Journal] CitaLaw: Enhancing LLM with Citations in Legal Domain Zhang et al. [paper]
- [2024] [Journal] Evaluation ethics of llms in legal domain Zhang et al. [paper]
- [2024] [Conference] Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models Kim et al. [paper]
- [2024] [Conference] IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning Joshi et al. [paper]
- [2024] [Conference] One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support Rasiah et al. [paper]
- [2024] [Journal] Legalbench-rag: A benchmark for retrieval-augmented generation in the legal domain Pipitone et al. [paper]
- [2024] [Conference] RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content Monteiro et al. [paper]
- [2023] [Journal] Benchmarking legal knowledge of large language models Fei et al. [paper]
- [2023] [Conference] LEGALBENCH: a collaboratively built benchmark for measuring legal reasoning in large language models Guha et al. [paper]
- [2023] [Journal] Disc-lawllm: Fine-tuning large language models for intelligent legal services Yue et al. [paper]
- [2025] [Journal] RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity Santosh et al. [paper]
- [2025] [Journal] Effectiveness in retrieving legal precedents: exploring text summarization and cutting-edge language models toward a cost-efficient approach Mentzingen et al. [paper]
- [2025] [Journal] Leveraging large language models for abstractive summarization of Italian legal news Benedetto et al. [paper]
- [2024] [Journal] Summarizing long regulatory documents with a multi-step pipeline Sie et al. [paper]
- [2024] [Conference] LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English T.y.s.s et al. [paper]
- [2024] [Journal] CaseSumm: A Large-Scale Dataset for Long-Context Summarization from US Supreme Court Opinions Heddaya et al. [paper]
- [2024] [Journal] Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland Rolshoven et al. [paper]
- [2024] [Journal] Llamandement: Large language models for summarization of french legislative proposals Gesnouin et al. [paper]
- [2024] [Journal] Lawsuit: a large expert-written summarization dataset of italian constitutional court verdicts Ragazzi et al. [paper]
- [2024] [Journal] Low-resource court judgment summarization for common law systems Liu et al. [paper]
- [2024] [Journal] Applicability of large language models and generative models for legal case judgement summarization Deroy et al. [paper]
- [2023] [Journal] How ready are pre-trained abstractive models and LLMs for legal case judgement summarization? Deroy et al. [paper]
- [2022] [Journal] Chain-of-thought prompting elicits reasoning in large language models Wei et al. [paper]
- [2025] [Journal] Leveraging LLMs for legal terms extraction with limited annotated data Breton et al. [paper]
- [2023] [Conference] A Comparative Study of Prompting Strategies for Legal Text Classification Parizi et al. [paper]
- [2023] [Conference] Exploring the effectiveness of prompt engineering for legal reasoning tasks Yu et al. [paper]
- [2023] [Journal] Llmediator: Gpt-4 assisted online dispute resolution Westermann et al. [paper]
Feel free to ask any questions or provide us with some suggestions via:
- Congqing He: hecongqing@hotmail.com