VeriCoT：基於邏輯一致性檢驗的神經符號思維鏈驗證

摘要

大型語言模型（LLM）能夠透過思維鏈（CoT）進行多步驟推理，但無法可靠地驗證自身邏輯。即使得出正確答案，其底層推理過程可能存在缺陷，這在高風險應用場景中會削弱可信度。為緩解此問題，我們提出 VeriCoT——一種從 CoT 推理中提取並驗證形式邏輯論證的神經符號方法。VeriCoT 將每個 CoT 推理步驟形式化為一階邏輯，並識別將論證錨定於原始上下文、常識知識或先前推理步驟的前提條件。符號化表徵使自動求解器能夠驗證邏輯有效性，而自然語言前提則允許人類和系統識別未錨定或謬誤的推理步驟。在 ProofWriter、LegalBench 和 BioASQ 數據集上的實驗表明，VeriCoT 能有效識別缺陷推理，並可作為最終答案正確性的強力預測指標。我們還利用 VeriCoT 的驗證信號實現：(1) 推論階段的自我反思，(2) 對 VeriCoT 蒸餾數據集進行監督式微調（SFT），以及 (3) 透過基於驗證的成對獎勵進行直接偏好優化（DPO）的偏好微調（PFT），從而進一步提升推理的有效性與準確性。

English

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.

VeriCoT：基於邏輯一致性檢驗的神經符號思維鏈驗證

VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks

摘要

Support