{"ID":2843491,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08392","arxiv_id":"2511.08392","title":"PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints","abstract":"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.","short_abstract":"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. Eac...","url_abs":"https://arxiv.org/abs/2511.08392","url_pdf":"https://arxiv.org/pdf/2511.08392v1","authors":"[\"Tangrui Li\",\"Pei Wang\",\"Hongzheng Wang Christian Hahm\",\"Matteo Spatola\",\"Justin Shi\"]","published":"2025-11-11T16:10:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}