mlsanityData to 7 Oct 2026

PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements

arXiv 2506.00608 ↗First posted 31 May 2025cs.CLcited by 1

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

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  8. 2025Gemma 3 Technical Reportcited by 1,686
  9. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  11. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  12. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 232
20 more
  1. 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 145
  2. 2024SaulLM-7B: A pioneering Large Language Model for Lawcited by 136
  3. 2023Large Language Models in Law: A Surveycited by 128
  4. 2024LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domaincited by 113
  5. 2024CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answeringcited by 70
  6. 2023LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Modelscited by 66
  7. 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 65
  8. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
  9. 2024SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domaincited by 39
  10. 2024LawLLM: Law Large Language Model for the US Legal Systemcited by 37
  11. 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
  12. 2023MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understandingcited by 32
  13. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generationcited by 31
  14. 2025Towards Robust Legal Reasoning: Harnessing Logical LLMs in Lawcited by 30
  15. 2025Multi-Agent Simulator Drives Language Models for Legal Intensive Interactioncited by 22
  16. 2024RAG based Question-Answering for Contextual Response Prediction Systemcited by 14
  17. 2023EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learningcited by 13
  18. 2025QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performancecited by 6
  19. 2021Detecting Logical Relation In Contract Clausescited by 2
  20. 2025NitiBench: A Comprehensive Study of LLM Framework Capabilities for Thai Legal Question Answeringcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
  2. 2026LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence
  3. 2025Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
  4. 2026From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation
  5. 2025A Reasoning-Focused Legal Retrieval Benchmark
  6. 2026LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law
  7. 2024Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents
  8. 2024LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation