BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Journal:
arXiv
Published Date:
May 18, 2025
Abstract
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.
