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

arXiv: https://arxiv.org/abs/2404.09129 · HTML: https://mlsanity.com/paper/2404.09129/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 14 Apr 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 14 of 14)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)

## Built on by (most cited first, 12 of 12)

- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning](https://mlsanity.com/paper/2505.16270/) (2025)
- [Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement](https://mlsanity.com/paper/2506.01663/) (2025)
- [Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning](https://mlsanity.com/paper/2406.12050/) (2024)
- [DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling](https://mlsanity.com/paper/2506.16043/) (2025)
- [From Emergence to Control: Probing and Modulating Self-Reflection in Language Models](https://mlsanity.com/paper/2506.12217/) (2025)
- [What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction](https://mlsanity.com/paper/2507.15152/) (2025)
- [Topic Classification of Case Law Using a Large Language Model and a New Taxonomy for UK Law: AI Insights into Summary Judgment](https://mlsanity.com/paper/2405.12910/) (2024)
- [Positive Experience Reflection for Agents in Interactive Text Environments](https://mlsanity.com/paper/2411.02223/) (2024)
- [Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale](https://mlsanity.com/paper/2601.18730/) (2026)
- [Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds](https://mlsanity.com/paper/2607.28908/) (2026)
- [COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models](https://mlsanity.com/paper/2608.17234/) (2026)

## Abstract (arXiv)

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.