让大模型推理每步都可验证，提升逻辑可信度
PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints
- 每步推理显式标注前提、规则和结论，强制单步推导
- 支持链级验证，在黑箱环境下也能确保逻辑正确性
- 适合需要高可靠性推理的场景，如安全关键系统
大语言模型常缺乏逻辑连贯性，从前提到结论的推导不遵循明确推理规则。本文提出证明携带式推理框架PCRLLM，约束推理过程为单步推导，同时保持自然语言表达。每个输出显式包含前提、推理规则与结论，支持基于目标逻辑的验证。该机制在黑盒环境下仍可实现链级验证，缓解可信度担忧。此外，PCRLLM促进多模型协同，使中间步骤能在形式规则下对比与整合。最后，我们设计了生成大规模逐步推理数据的基准方案，融合自然语言表达力与形式严谨性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often exhibit limited logical coherence, mapping premises to conclusions without adherence to explicit inference rules. We propose Proof-Carrying Reasoning with LLMs (PCRLLM), a framework that constrains reasoning to single-step inferences while preserving natural language formulations. Each output explicitly specifies premises, rules, and conclusions, thereby enabling verification against a target logic. This mechanism mitigates trustworthiness concerns by supporting chain-level validation even in black-box settings. Moreover, PCRLLM facilitates systematic multi-LLM collaboration, allowing intermediate steps to be compared and integrated under formal rules. Finally, we introduce a benchmark schema for generating large-scale step-level reasoning data, combining natural language expressiveness with formal rigor.
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。