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

Anonymous

TL;DR: This paper explores self-reflective prompting in Large Language Models without external feedback, demonstrates effects of comprehension and question difficulty on self-reflection efficacy, and suggests implementation guidelines.

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.

Paper Type: short

Research Area: Interpretability and Analysis of Models for NLP

Contribution Types: Model analysis & interpretability, Reproduction study

Languages Studied: English