用强化学习让大模型回答更靠谱，确保每句话都有证据支持。
EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models
- 通过评分机制评估回复的证据一致性与正确性，用强化学习优化生成。
- 在医疗和法律领域，证据支持率提升近2倍，幻觉减少5倍。
- 适合需要高可信度回答的应用，如医疗诊断、法律推理。
大语言模型虽流畅，却易产生无证据支撑的幻觉，尤其在医疗、法律等高风险领域危害显著。本文提出EvidenceRL，一种基于强化学习的训练框架，通过评分机制评估候选回复的证据蕴含性（与检索证据及上下文的一致性）与正确性，并采用组相对策略优化（GRPO）进行训练。在心脏诊断与法律推理两个高风险领域测试表明，EvidenceRL显著提升证据依从性与忠实度：在Llama-3.2-3B上，心脏诊断任务中F1@3从37.0升至54.5，证据支持率从31.8%增至61.6%，幻觉下降近5倍；在Llama-3.1-8B上，法律推理任务忠实度从32.8%升至67.6%，行为改进一致。代码已开源。
原文摘要 · Abstract (English)
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 \textbf{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 ($G_{\max}@3$) rises from 47.6 to 78.2; hallucinations drop nearly 5$\times$ 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。