PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints
This addresses trustworthiness concerns in LLM reasoning for applications requiring formal validation, though it appears incremental as it builds on existing stepwise reasoning methods.
The paper tackles the problem of limited logical coherence in Large Language Models by proposing PCRLLM, a framework that constrains reasoning to single-step inferences with explicit premises, rules, and conclusions, enabling verification and improving trustworthiness.
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.