When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models

Yanhong Li, Chenghao Yang, Allyson Ettinger


Abstract
Recent studies suggest that self-reflective prompting can significantly enhance the reasoning capabilities of Large Language Models (LLMs). However, the use of external feedback as a stop criterion raises doubts about the true extent of LLMs’ ability to emulate human-like self-reflection. In this paper, we set out to clarify these capabilities under a more stringent evaluation setting in which we disallow any kind of external feedback. Our findings under this setting show a split: while self-reflection enhances performance in TruthfulQA, it adversely affects results in HotpotQA.We conduct follow-up analyses to clarify the contributing factors in these patterns, and find that the influence of self-reflection is impacted both by reliability of accuracy in models’ initial responses, and by overall question difficulty: specifically, self-reflection shows the most benefit when models are less likely to be correct initially, and when overall question difficulty is higher. We also find that self-reflection reduces tendency toward majority voting. Based on our findings, we propose guidelines for decisions on when to implement self-reflection. We release the codebase for reproducing our experiments at https://github.com/yanhong-lbh/LLM-SelfReflection-Eval.
Anthology ID:
2024.findings-naacl.237
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3741–3753
Language:
URL:
https://aclanthology.org/2024.findings-naacl.237
DOI:
10.18653/v1/2024.findings-naacl.237
Bibkey:
Cite (ACL):
Yanhong Li, Chenghao Yang, and Allyson Ettinger. 2024. When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3741–3753, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models (Li et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.237.pdf