mlsanityData to 7 Oct 2026

Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture

arXiv 2306.16092 ↗First posted 28 Jun 2023cs.CLcited by 119

On the map: LLM agents and tool use → Social simulation and multi-agent debate

also in 1 more
Abstract (arXiv)

Artificial Intelligence (AI) holds great potential in legal services, yet Large Language Models (LLMs) face two major challenges: limited knowledge of the Chinese legal system and vulnerability to hallucinations. To address these issues, we present Chatlaw, a multi-agent legal assistant. Chatlaw's framework is designed to emulate the Standard Operating Procedures (SOP) of real law firms, where different roles (e.g., assistant, researcher, senior lawyer) collaborate on a case. To computationally mirror this collaborative structure, we developed a novel Role-Aligned Mixture-of-Experts (RA-MoE) architecture. In this system, the internal "experts" are specifically trained to align with the distinct tasks of each agent role (e.g., inquiry, analysis, drafting). These specialized agents (Legal Assistant, Researcher, etc.) then form the collaborative framework. When they interact with users, retrieve legal knowledge, analyze case details, or generate reliable consultations, the RA-MoE architecture intelligently routes their computations to the corresponding dedicated expert, ensuring each step is handled by the most qualified parameters. In evaluations, Chatlaw surpasses general-purpose AI models, including GPT-4, achieving a 7.73% improvement in accuracy on the LawBench benchmark and an 11-point higher score on the Unified Qualification Exam for Legal Professionals. Real-case studies and expert assessments further confirm its robustness. Chatlaw enhances the accessibility and reliability of legal services, advancing the provision of legal support to the public.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 18 of its 65 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

18 of 65 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  7. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  9. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  10. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  11. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  12. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
6 more
  1. 2022DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalecited by 403
  2. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 302
  3. 2022polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informaticscited by 48
  4. 2023A Brief Report on LawGPT 1.0: A Virtual Legal Assistant Based on GPT-3cited by 46
  5. 2022Augmenting Interpretable Models with LLMs during Trainingcited by 36
  6. 2023Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Modelcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 23; 2024: 41; 2025: 27; 2026: 28.

119 papers.

Sort:

By area:

  1. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  2. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  3. 2023EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Educationcited by 80
  4. 2024MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learningcited by 63
  5. 2024GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capabilitycited by 57
  6. 2023EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commercecited by 48
  7. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  8. 2024Learning or Self-aligning? Rethinking Instruction Fine-tuningcited by 43
  9. 2023Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucinationcited by 41
  10. 2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
  11. 2024Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Modelscited by 38
  12. 2024TelecomGPT: A Framework to Build Telecom-Specfic Large Language Modelscited by 38
38 more
  1. 2023Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Taskscited by 36
  2. 2024AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agentscited by 36
  3. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  4. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 30
  5. 2024SciLitLLM: How to Adapt LLMs for Scientific Literature Understandingcited by 29
  6. 2023ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovationcited by 25
  7. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  8. 2024BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Modelscited by 15
  9. 2023FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Promptcited by 14
  10. 2025A Survey on Agent Workflow -- Status and Futurecited by 14
  11. 2024RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answeringcited by 13
  12. 2025Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoningcited by 13
  13. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  14. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11
  15. 2024Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answeringcited by 11
  16. 2024Octopus v4: Graph of language modelscited by 11
  17. 2025Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domainscited by 11
  18. 2025LegalDelta: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gaincited by 11
  19. 2023Unifying Corroborative and Contributive Attributions in Large Language Modelscited by 10
  20. 2025Federated Retrieval Augmented Generation for Multi-Product Question Answeringcited by 10
  21. 2025Rethinking Reward Models for Multi-Domain Test-Time Scalingcited by 10
  22. 2023LAiW: A Chinese Legal Large Language Models Benchmarkcited by 9
  23. 2023Machine Mindset: An MBTI Exploration of Large Language Modelscited by 9
  24. 2025Large Language Models Meet Legal Artificial Intelligence: A Surveycited by 9
  25. 2024LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Datasetcited by 8
  26. 2024Evaluation Ethics of LLMs in Legal Domaincited by 8
  27. 2025Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Studycited by 8
  28. 2023AcademicGPT: Empowering Academic Researchcited by 6
  29. 2024Exploring the Nexus of Large Language Models and Legal Systems: A Short Surveycited by 6
  30. 2024Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reportscited by 6
  31. 2025Mitigating Unintended Memorization with LoRA in Federated Learning for LLMscited by 6
  32. 2023FedJudge: Federated Legal Large Language Modelcited by 5
  33. 2023Construction contract risk identification based on knowledge-augmented language modelcited by 5
  34. 2024StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generationcited by 5
  35. 2024LLeMpower: Understanding Disparities in the Control and Access of Large Language Modelscited by 5
  36. 2024CourseGPT-zh: an Educational Large Language Model Based on Knowledge Distillation Incorporating Prompt Optimizationcited by 5
  37. 2024It Cannot Be Right If It Was Written by AI: On Lawyers' Preferences of Documents Perceived as Authored by an LLM vs a Humancited by 5
  38. 2024Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Modelscited by 5

50 most cited of 119 All 119 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation
  2. 2025Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments
  3. 2024A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement
  4. 2026Investigating Multi-Agent Deliberation in Law
  5. 2024AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation
  6. 2026NyayaAI: An AI-Powered Legal Assistant Using Multi-Agent Architecture and Retrieval-Augmented Generation
  7. 2025Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction
  8. 2024LegalAgentBench: Evaluating LLM Agents in Legal Domain