mlsanityData to 14 Oct 2026

EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models

arXiv 2603.19532 ↗First posted 20 Mar 2026cs.CL cs.IR cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are fluent but prone to hallucinations, producing answers that appear plausible yet are unsupported by available evidence. This failure is especially problematic in high-stakes domains where decisions must be justified by verifiable information. We introduce EvidenceRL, a reinforcement learning framework that enforces evidence adherence during training. EvidenceRL scores candidate responses for grounding (entailment with retrieved evidence and context) and correctness (agreement with reference answers) and optimizes the generator using Group Relative Policy Optimization (GRPO). We evaluate across two high-stakes domains, cardiac diagnosis and legal reasoning, where EvidenceRL consistently improves evidence grounding and faithfulness without sacrificing task accuracy. On cardiac diagnosis, F1@3 increases from 37.0 to 54.5 on Llama-3.2-3B while grounding (Gmax@3) rises from 47.6 to 78.2; hallucinations drop nearly 5× and evidence-supported diagnoses increase from 31.8% to 61.6%. On legal reasoning, EvidenceRL raises Faithfulness from 32.8% to 67.6% on Llama-3.1-8B, demonstrating consistent behavioral change across domains. Our code is open-sourced at https://github.com/Wizaaard/EvidenceRL.git.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

32 of 53 references.

References · 32

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  6. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  9. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  10. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  11. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  12. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
20 more
  1. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  2. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  3. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  4. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  5. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  6. 2021QuestEval: Summarization Asks for Fact-based Evaluationcited by 244
  7. 2023Fine-tuning Language Models for Factualitycited by 221
  8. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 176
  9. 2018Lessons from Natural Language Inference in the Clinical Domaincited by 151
  10. 2023Factuality Challenges in the Era of Large Language Modelscited by 126
  11. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 101
  12. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  13. 2024IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neuronscited by 38
  14. 2025A Reasoning-Focused Legal Retrieval Benchmarkcited by 37
  15. 2024RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Modelscited by 25
  16. 2025Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approachcited by 25
  17. 2025DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMscited by 25
  18. 2024Correctness is not Faithfulness in RAG Attributionscited by 18
  19. 2024PA-RAG: RAG Alignment via Multi-Perspective Preference Optimizationcited by 11
  20. 2025CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QAcited by 0
  2. 2026Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learningcited by 0
  3. 2026Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPOcited by 0
  4. 2026ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reportscited by 0
  5. 2026SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
  2. 2025TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
  3. 2026Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models
  4. 2026Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning
  5. 2026Evidence-State Rewards for Long-Context Reasoning
  6. 2026MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning
  7. 2025Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning
  8. 2026Learning Evidence Highlighting for Frozen LLMs