VeriCoT：通过逻辑一致性检查进行神经符号思维链验证
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
AI总结：
VeriCoT 通过将思维链推理步骤形式化为一阶逻辑并进行一致性验证，以识别逻辑缺陷并预测答案正确性，同时利用验证信号改进推理与微调。
摘要：
大语言模型（LLM）能够通过思维链（Chain-of-Thought, CoT）执行多步推理，但无法可靠地验证其自身逻辑。即使它们得出了正确答案，其底层推理也可能存在缺陷，从而削弱高风险场景下的可信度。为缓解这一问题，我们提出了 VeriCoT，一种从 CoT 推理中提取并验证形式化逻辑论证的神经符号方法。VeriCoT 将每个 CoT 推理步骤形式化为一阶逻辑，并识别将论证建立在源上下文、常识知识或先前推理步骤之上的前提。符号化表示使自动化求解器能够验证逻辑有效性，而自然语言前提则允许人类和系统识别缺乏依据或存在谬误的推理步骤。在 ProofWriter、LegalBench 和 BioASQ 数据集上的实验表明，VeriCoT 能有效识别有缺陷的推理，并可作为最终答案正确性的强预测指标。我们还利用 VeriCoT 的验证信号进行：（1）推理时自反思，（2）在 VeriCoT 蒸馏数据集上进行监督微调（SFT），以及（3）使用基于验证的成对奖励进行直接偏好优化（DPO）的偏好微调（PFT），从而进一步提高推理有效性和准确性。
英文摘要：
LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, undermining trust in high-stakes scenarios. To mitigate this issue, we introduce VeriCoT, a neuro-symbolic method that extracts and verifies formal logical arguments from CoT reasoning. VeriCoT formalizes each CoT reasoning step into first-order logic and identifies premises that ground the argument in source context, commonsense knowledge, or prior reasoning steps. The symbolic representation enables automated solvers to verify logical validity while the NL premises allow humans and systems to identify ungrounded or fallacious reasoning steps. Experiments on the ProofWriter, LegalBench, and BioASQ datasets show VeriCoT effectively identifies flawed reasoning, and serves as a strong predictor of final answer correctness. We also leverage VeriCoT's verification signal for (1) inference-time self-reflection, (2) supervised fine-tuning (SFT) on VeriCoT-distilled datasets and (3) preference fine-tuning (PFT) with direct preference optimization (DPO) using verification-based pairwise rewards, further improving reasoning validity and accuracy.
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。
