Reasoning-CV：为知识辅助声明验证微调具备强推理能力的大语言模型
Reasoning-CV: Fine-tuning Powerful Reasoning LLMs for Knowledge-Assisted Claim Verification
AI总结：
针对现有声明验证“分解后验证”范式易在分解阶段引入错误的问题，提出CoT-Verify范式及Reasoning-CV微调方法，仅用8B预训练LLM就实现了优于现有方法及多款黑盒大模型的知识辅助声明验证效果。
摘要：
声明验证在打击错误信息中至关重要，大语言模型（LLM）近期已成为该领域利用外部知识评估声明真实性的强大工具。现有基于LLM的声明验证方法通常采用“分解后验证”范式，即把复杂声明拆分为多个独立子声明后分别验证，但该范式往往会在声明分解过程中引入错误。为缓解这类错误，我们提出构建“思维链验证（CoT-Verify）”范式，借助LLM推理方法为原始复杂声明生成思维链验证路径，无需将声明分解为子声明，也无需设置独立的验证阶段。基于CoT-Verify范式，我们提出了名为Reasoning-CV的自然微调方法，以增强LLM的验证能力，该方法包含监督微调（SFT）阶段和自我改进直接偏好优化（DPO）阶段。仅使用一个8B参数的预训练LLM，Reasoning-CV在知识辅助声明验证任务上的表现就优于现有“分解后验证”方法，也优于GPT-4o+CoT、o1-preview等强大的黑盒LLM。我们的代码已公开。
英文摘要：
Claim verification is essential in combating misinformation, and large language models (LLMs) have recently emerged in this area as powerful tools for assessing the veracity of claims using external knowledge. Existing LLM-based methods for claim verification typically adopt a Decompose-Then-Verify paradigm, which involves decomposing complex claims into several independent sub-claims and verifying each sub-claim separately. However, this paradigm often introduces errors during the claim decomposition process. To mitigate these errors, we propose to develop the Chain-of-Thought (CoT)-Verify paradigm, which leverages LLM reasoning methods to generate CoT-verification paths for the original complex claim without requiring decompositions into sub-claims and separate verification stages. The CoT-Verify paradigm allows us to propose a natural fine-tuning method called Reasoning-CV to enhance the verification capabilities in LLMs. Reasoning-CV includes a supervised fine-tuning (SFT) stage and a self-improvement direct preference optimization (DPO) stage. Utilizing only an 8B pre-trained LLM, Reasoning-CV demonstrates superior knowledge-assisted claim verification performances compared to existing Decompose-Then-Verify methods, as well as powerful black-box LLMs such as GPT-4o+CoT and o1-preview. Our code is available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
