让大模型推理更可靠，实时发现并修正事实错误。
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
- 推理链中提取事实主张，实时检测知识不一致。
- 利用外部知识低成本精准修正错误，保持推理连贯性。
- 适合需要高准确性的长链条推理任务，如科学问答。
推理语言模型（RLMs）通过扩展推理链显著提升了复杂任务的表现，但在知识密集型任务中容易产生事实错误。为解决此问题，我们提出CheckRLM框架，通过检索增强生成（RAG）在推理过程中及时检查并修正事实错误。具体而言，CheckRLM从推理链中提取事实主张，识别并定位推理性过程中的细微知识不一致。一旦检测到错误，通过调用外部知识，以低开销但高精度的方式执行最小化修正，确保推理链与正确知识的一致性。大量实验表明，CheckRLM显著优于现有基线，在长周期推理中有效缓解错误累积，且成本更低。代码与数据已公开于https://github.com/AI9Stars/CheckRLM。
原文摘要 · Abstract (English)
Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks. To address this issue, we propose CheckRLM, a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors. Specifically, CheckRLM extracts factual claims from the reasoning chain to identify and localize subtle knowledge inconsistencies during inference. Upon detection of errors, a refinement mechanism performs minimal-cost yet precise corrections by leveraging external knowledge, ensuring coherence between the reasoning chain and correct knowledge. Extensive experiments demonstrate that CheckRLM substantially outperforms existing baselines, exhibiting a strong capability to mitigate error accumulation in long-horizon reasoning with lower costs. The code and data are available at https://github.com/AI9Stars/CheckRLM.
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。