BARREL：面向事實性與可靠性的邊界感知推理大語言模型

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

May 18, 2025

作者: Junxiao Yang, Jinzhe Tu, Haoran Liu, Xiaoce Wang, Chujie Zheng, Zhexin Zhang, Shiyao Cui, Caishun Chen, Tiantian He, Hongning Wang, Yew-Soon Ong, Minlie Huang

cs.AI

摘要

近期，大型推理模型（LRMs）在數學和邏輯推理方面展現了令人矚目的能力。然而，當前的LRMs很少承認無知或回應「我不知道」，反而經常在表現出過度自信的同時給出錯誤答案，這引發了對其事實可靠性的擔憂。在本研究中，我們識別了兩種由過度思考導致的病態推理模式，它們助長了過度自信和錯誤答案的產生：最後一刻的猜測和二次思考的螺旋。為解決這些問題，我們提出了BARREL——一個促進簡潔且邊界感知的事實推理的新框架。我們的實驗表明，BARREL訓練將DeepSeek-R1-Distill-Llama-8B的可靠性從39.33%提升至61.48%，同時仍能達到與基於R1生成的推理數據微調的模型相當的準確度。這些結果證明，我們的先導研究對於構建更可靠且基於事實的系統2 LRMs具有啟發意義。

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.