测试发现大模型反思能力差，常重复犯错，无法真正自我修正。
Illusions of reflection: open-ended task reveals systematic failures in Large Language Models' reflective reasoning
- 设计开放但有约束的科学试题生成任务，检验模型反思效果。
- 首次生成仅约1个有效题目（均值），反思后仍仅小幅提升至约1个。
- 多数错误重复出现，说明反思非基于原则性修正，而是偶然产出。
人类不仅能事后发现错误，更能在过程中通过与目标和约束关联的‘反思’即时纠正。当前大语言模型虽生成推理文本和‘反思’内容，但其是否具备类人反思能力尚不明确。以往研究多基于封闭任务（具明确外部正确性信号），易掩盖自我修正能力的局限。本文在开放但规则受限的真实任务中测试八款前沿模型：生成有效的科学测试题，并根据自身批判进行修订。首次生成表现差（常0个有效题，均值≈1），反思后提升有限（仍≈1）。关键发现是第二次尝试常重复相同错误，表明改进主要源于偶然产生有效题，而非错误识别与原则性修复。随着任务开放性增加，反思前后的性能均下降；宣称具有‘推理能力’的模型亦无优势。结果表明，当前大模型的‘反思’缺乏人类那种主动、目标驱动的监控机制，难以在初次就遵守约束。除非在模型内部实现此类机制，否则可靠表现需依赖外部强制约束结构。代码已开源。
原文摘要 · Abstract (English)
Humans do not just find mistakes after the fact -- we often catch them mid-stream because 'reflection' is tied to the goal and its constraints. Today's large language models produce reasoning tokens and 'reflective' text, but is it functionally equivalent with human reflective reasoning? Prior work on closed-ended tasks -- with clear, external 'correctness' signals -- can make 'reflection' look effective while masking limits in self-correction. We therefore test eight frontier models on a simple, real-world task that is open-ended yet rule-constrained, with auditable success criteria: to produce valid scientific test items, then revise after considering their own critique. First-pass performance is poor (often zero valid items out of 4 required; mean $\approx$ 1), and reflection yields only modest gains (also $\approx$ 1). Crucially, the second attempt frequently repeats the same violation of constraint, indicating 'corrective gains' arise largely from chance production of a valid item rather than error detection and principled, constraint-sensitive repair. Performance before and after reflection deteriorates as open-endedness increases, and models marketed for 'reasoning' show no advantage. Our results suggest that current LLM 'reflection' lacks functional evidence of the active, goal-driven monitoring that helps humans respect constraints even on a first pass. Until such mechanisms are instantiated in the model itself, reliable performance requires external structure that enforces constraints. Our code is available at: https://github.com/cruiseresearchgroup/LLM_ReflectionTest
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。