Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance

Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Junqi Dai, Qinyuan Cheng, Xuanjing Huang, Xipeng Qiu


Abstract
Machine reasoning, which involves solving complex problems through step-by-step deduction and analysis, is a crucial indicator of the capabilities of Large Language Models (LLMs). However, as the complexity of tasks escalates, LLMs often encounter increasing errors in their multi-step reasoning process. This study delves into the underlying factors contributing to these reasoning errors and seeks to leverage uncertainty to refine them. Specifically, we introduce Uncertainty-aware Adaptive Guidance (UAG), a novel approach for guiding LLM reasoning onto an accurate and reliable trajectory. UAG first identifies and evaluates uncertainty signals within each step of the reasoning chain. Upon detecting a significant increase in uncertainty, UAG intervenes by retracting to a previously reliable state and then introduces certified reasoning clues for refinement. By dynamically adjusting the reasoning process, UAG offers a plug-and-play solution for improving LLMs’ performance in complex reasoning. Extensive experiments across various reasoning tasks demonstrate that UAG not only enhances the reasoning abilities of LLMs but also consistently outperforms several strong baselines with minimal computational overhead. Further analysis reveals that UAG is notably effective in identifying and diminishing reasoning errors.
Anthology ID:
2024.acl-long.131
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2401–2416
Language:
URL:
https://aclanthology.org/2024.acl-long.131
DOI:
10.18653/v1/2024.acl-long.131
Bibkey:
Cite (ACL):
Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Junqi Dai, Qinyuan Cheng, Xuanjing Huang, and Xipeng Qiu. 2024. Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2401–2416, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance (Yin et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.131.pdf