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

arXiv: https://arxiv.org/abs/2306.16092 · HTML: https://mlsanity.com/paper/2306.16092/

## Key facts

- Cited by 122 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)
- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics](https://mlsanity.com/paper/2209.14803/) (2022)
- [A Brief Report on LawGPT 1.0: A Virtual Legal Assistant Based on GPT-3](https://mlsanity.com/paper/2302.05729/) (2023)
- [Augmenting Interpretable Models with LLMs during Training](https://mlsanity.com/paper/2209.11799/) (2022)
- [Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model](https://mlsanity.com/paper/2304.02169/) (2023)

## Built on by (most cited first, 30 of 122)

- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education](https://mlsanity.com/paper/2308.02773/) (2023)
- [MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning](https://mlsanity.com/paper/2402.11260/) (2024)
- [GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability](https://mlsanity.com/paper/2403.04483/) (2024)
- [EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce](https://mlsanity.com/paper/2308.06966/) (2023)
- [A Survey of Large Language Model Agents for Question Answering](https://mlsanity.com/paper/2503.19213/) (2025)
- [Learning or Self-aligning? Rethinking Instruction Fine-tuning](https://mlsanity.com/paper/2402.18243/) (2024)
- [An Intelligent Agentic System for Complex Image Restoration Problems](https://mlsanity.com/paper/2410.17809/) (2024)
- [Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination](https://mlsanity.com/paper/2311.15548/) (2023)
- [TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models](https://mlsanity.com/paper/2407.09424/) (2024)
- [Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models](https://mlsanity.com/paper/2403.03432/) (2024)
- [AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents](https://mlsanity.com/paper/2408.08089/) (2024)
- [Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2311.11608/) (2023)
- [Exploring Autonomous Agents through the Lens of Large Language Models: A Review](https://mlsanity.com/paper/2404.04442/) (2024)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding](https://mlsanity.com/paper/2408.15545/) (2024)
- [ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation](https://mlsanity.com/paper/2307.15290/) (2023)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models](https://mlsanity.com/paper/2403.18365/) (2024)
- [FoodGPT: A Large Language Model in Food Testing Domain with Incremental Pre-training and Knowledge Graph Prompt](https://mlsanity.com/paper/2308.10173/) (2023)
- [A Survey on Agent Workflow -- Status and Future](https://mlsanity.com/paper/2508.01186/) (2025)
- [RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering](https://mlsanity.com/paper/2402.16457/) (2024)
- [Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning](https://mlsanity.com/paper/2502.07912/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [LegalDelta: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain](https://mlsanity.com/paper/2508.12281/) (2025)
- [Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective](https://mlsanity.com/paper/2402.00262/) (2024)
- [Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering](https://mlsanity.com/paper/2402.08277/) (2024)
- [Octopus v4: Graph of language models](https://mlsanity.com/paper/2404.19296/) (2024)
- [Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains](https://mlsanity.com/paper/2501.14431/) (2025)

## 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.