mlsanityData to 14 Oct 2026

CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation

arXiv 2508.05534 ↗First posted 7 Aug 2025cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Due to their ability to process long and complex contexts, LLMs can offer key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfaithful, ungrounded, or hallucinatory outputs. While Retrieval-Augmented Generation offers a promising solution by grounding generations in external knowledge, it offers no guarantee that the provided context will be effectively integrated. To address this, context-aware decoding strategies have been proposed to amplify the influence of relevant context, but they usually do not explicitly enforce faithfulness to the context. In this work, we introduce Confidence-guided Copy-based Decoding for Legal Text Generation (CoCoLex)-a decoding strategy that dynamically interpolates the model produced vocabulary distribution with a distribution derived based on copying from the context. CoCoLex encourages direct copying based on the model's confidence, ensuring greater fidelity to the source. Experimental results on five legal benchmarks demonstrate that CoCoLex outperforms existing context-aware decoding methods, particularly in long-form generation tasks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 49 of its 77 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

49 of 77 references.

References · 49

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  11. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  12. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
37 more
  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  2. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  3. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  4. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  5. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  6. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  7. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  8. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 176
  9. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  10. 2024SaulLM-7B: A pioneering Large Language Model for Lawcited by 142
  11. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  12. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  13. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  14. 2021Adaptive Semiparametric Language Modelscited by 83
  15. 2024Enhancing Contextual Understanding in Large Language Models through Contrastive Decodingcited by 49
  16. 2023A Survey on Long Text Modeling with Transformerscited by 47
  17. 2021Mention Memory: incorporating textual knowledge into Transformers through entity mention attentioncited by 43
  18. 2022Retrieval-Augmented Transformer for Image Captioningcited by 38
  19. 2023Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Predictioncited by 38
  20. 2024AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledgecited by 37
  21. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  22. 2021Yes, BM25 is a Strong Baseline for Legal Case Retrievalcited by 24
  23. 2023Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructionscited by 24
  24. 2024Leveraging Large Language Models for Learning Complex Legal Concepts through Storytellingcited by 23
  25. 2023Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrievalcited by 20
  26. 2024Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contextscited by 19
  27. 2024CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generationcited by 18
  28. 2024Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistencycited by 14
  29. 2023DALE: Generative Data Augmentation for Low-Resource Legal NLPcited by 12
  30. 2024ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Taskscited by 11
  31. 2023KNN-LM Does Not Improve Open-ended Text Generationcited by 10
  32. 2024Enhancing Legal Compliance and Regulation Analysis with Large Language Modelscited by 10
  33. 2024The Factuality of Large Language Models in the Legal Domaincited by 10
  34. 2024A Reality Check on Context Utilisation for Retrieval-Augmented Generationcited by 9
  35. 2024Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documentscited by 5
  36. 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
  37. 2025Where is this coming from? Making groundedness count in the evaluation of Document VQA modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025Copy-Paste to Mitigate Large Language Model Hallucinationscited by 2
  2. 2026ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detectioncited by 2
  3. 2026ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Imagescited by 1
  4. 2026Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Modelscited by 1
  5. 2026Detecting Non-Membership in LLM Training Data via Rank Correlationscited by 0
  6. 2026LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
  2. 2024Improving Open-Ended Text Generation via Adaptive Decoding
  3. 2026Enhancing Legal LLMs through Metadata-Enriched RAG Pipelines and Direct Preference Optimization
  4. 2025Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation
  5. 2025All for law and law for all: Adaptive RAG Pipeline for Legal Research
  6. 2026In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
  7. 2024LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain
  8. 2026Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG