让大模型学会说‘不知道’，减少盲目自信错误
BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
- 引入边界感知机制，避免过度推理导致的错误
- 使模型在数学逻辑任务中可靠率从39.33%提升至61.48%
- 适合追求真实可信推理结果的研究者与应用开发
大型推理模型（LRMs）在数学与逻辑推理方面表现突出，但往往缺乏对未知的承认，常以过度自信的姿态给出错误答案，引发事实可靠性担忧。本文识别出两种导致高自信错误的病理推理模式：最后一刻猜测和二次思考螺旋。为此提出BARREL框架，促进简洁且边界感知的事实性推理。实验表明，经BARREL训练后，DeepSeek-R1-Distill-Llama-8B的可靠性由39.33%提升至61.48%，同时保持与基于R1生成推理数据微调模型相当的准确率。该研究为构建更可靠、更具事实性的系统2型推理模型提供了有益探索。
原文摘要 · Abstract (English)
Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with "I don't know". Instead, they often produce incorrect answers while showing undue confidence, raising concerns about their factual reliability. In this work, we identify two pathological reasoning patterns characterized by overthinking that contribute to the overconfident and incorrect answers: last-minute guessing and second-thought spiraling. To address these issues, we propose BARREL-a novel framework that promotes concise and boundary-aware factual reasoning. Our experiments show that BARREL-training increases the reliability of DeepSeek-R1-Distill-Llama-8B from 39.33% to 61.48%, while still achieving accuracy comparable to models finetuned on reasoning data generated by R1. These results demonstrate that our pilot study is inspiring to build more reliable and factual System 2 LRMs.
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。