mlsanityData to 14 Oct 2026

GRAPH-GRPO-LEX: Contract Graph Modeling and Reinforcement Learning with Group Relative Policy Optimization

arXiv 2511.06618 ↗First posted 10 Nov 2025cs.AI cs.CL cs.LGcited by 1

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Contracts are complex documents featuring detailed formal structures, explicit and implicit dependencies and rich semantic content. Given these document properties, contract drafting and manual examination of contracts have proven to be both arduous and susceptible to errors. This work aims to simplify and automate the task of contract review and analysis using a novel framework for transforming legal contracts into structured semantic graphs, enabling computational analysis and data-driven insights. We introduce a detailed ontology mapping core legal contract elements to their graph-theoretic equivalents of nodes and edges. We then present a reinforcement learning based Large Language Model (LLM) framework for segmentation and extraction of entities and relationships from contracts. Our method, GRAPH-GRPO-LEX, incorporates both LLMs and reinforcement learning with group relative policy optimization (GRPO). By applying a carefully drafted reward function of graph metrics, we demonstrate the ability to automatically identify direct relationships between clauses, and even uncover hidden dependencies. Our introduction of the gated GRPO approach shows a strong learning signal and can move contract analysis from a linear, manual reading process to an easily visualized graph. This allows for a more dynamic analysis, including building the groundwork for contract linting similar to what is now practiced in software engineering.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 50 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

27 of 50 references.

References · 27

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  4. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  5. 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Modelscited by 336
  6. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  7. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  8. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 310
  9. 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 148
  10. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  11. 2024Large Concept Models: Language Modeling in a Sentence Representation Spacecited by 89
  12. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrieverscited by 84
15 more
  1. 2024Making Text Embedders Few-Shot Learnerscited by 79
  2. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
  3. 2025The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMscited by 74
  4. 2024Self-Boosting Large Language Models with Synthetic Preference Datacited by 40
  5. 2023A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecturecited by 28
  6. 2025KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichmentcited by 27
  7. 2024Toward General Instruction-Following Alignment for Retrieval-Augmented Generationcited by 9
  8. 2024LAW: Legal Agentic Workflows for Custody and Fund Services Contractscited by 6
  9. 2025The KL3M Data Project: Copyright-Clean Training Resources for Large Language Modelscited by 6
  10. 2023Construction contract risk identification based on knowledge-augmented language modelcited by 5
  11. 2025Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewardscited by 5
  12. 2023Automating construction contract review using knowledge graph-enhanced large language modelscited by 4
  13. 2024Automatic Knowledge Graph Construction for Judicial Casescited by 4
  14. 2025KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing Applicationscited by 4
  15. 2025Precise Legal Sentence Boundary Detection for Retrieval at Scale: NUPunkt and CharBoundarycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudicationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
  2. 2026Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
  3. 2025G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
  4. 2026Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
  5. 2026AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
  6. 2026A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction
  7. 2025Metadata Extraction Leveraging Large Language Models
  8. 2026ContractScrub: A benchmark for final review of legal contracts