PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements
Not on the map. Why?
Abstract (arXiv)
Contract review is a complex and time-intensive task that typically demands specialized legal expertise, rendering it largely inaccessible to non-experts. Moreover, legal interpretation is rarely straightforward-ambiguity is pervasive, and judgments often hinge on subjective assessments. Compounding these challenges, contracts are usually confidential, restricting their use with proprietary models and necessitating reliance on open-source alternatives. To address these challenges, we introduce PAKTON: a fully open-source, end-to-end, multi-agent framework with plug-and-play capabilities. PAKTON is designed to handle the complexities of contract analysis through collaborative agent workflows and a novel retrieval-augmented generation (RAG) component, enabling automated legal document review that is more accessible, adaptable, and privacy-preserving. Experiments demonstrate that PAKTON outperforms both general-purpose and pretrained models in predictive accuracy, retrieval performance, explainability, completeness, and grounded justifications as evaluated through a human study and validated with automated metrics.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 79 references that are in the map. First posted on arXiv 31 May 2025.
Builds on
32 of 79 references.
References · 32
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2024Qwen2.5 Technical Reportcited by 4,713
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
- 2025Gemma 3 Technical Reportcited by 1,686
- 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
- 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 232
20 more
- 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 145
- 2024SaulLM-7B: A pioneering Large Language Model for Lawcited by 136
- 2023Large Language Models in Law: A Surveycited by 128
- 2024LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domaincited by 113
- 2024CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answeringcited by 70
- 2023LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Modelscited by 66
- 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 65
- 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
- 2024SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domaincited by 39
- 2024LawLLM: Law Large Language Model for the US Legal Systemcited by 37
- 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
- 2023MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understandingcited by 32
- 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generationcited by 31
- 2025Towards Robust Legal Reasoning: Harnessing Logical LLMs in Lawcited by 30
- 2025Multi-Agent Simulator Drives Language Models for Legal Intensive Interactioncited by 22
- 2024RAG based Question-Answering for Contextual Response Prediction Systemcited by 14
- 2023EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learningcited by 13
- 2025QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performancecited by 6
- 2021Detecting Logical Relation In Contract Clausescited by 2
- 2025NitiBench: A Comprehensive Study of LLM Framework Capabilities for Thai Legal Question Answeringcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
- 2026LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence
- 2025Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
- 2026From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation
- 2025A Reasoning-Focused Legal Retrieval Benchmark
- 2026LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law
- 2024Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents
- 2024LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation