让大模型像人一样反思并修正错误，提升自我诊断能力。
Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models
- 基于认知心理学设计反思框架，分规划、监控、评估三步引导推理
- 自纠正成功率提升三倍，人类盲评中84%更信任其可信度
- 适合需要高可靠性推理的场景，如医疗、法律等专业领域
大型语言模型虽具备强大推理能力，但自我监控、诊断和纠错能力仍有限。本文提出一种心理基础的元认知框架，将安·布朗的调节循环（规划、监控、评估）转化为结构化提示机制，并集成于轻量级双过程元控制器中，实现自适应努力分配。在GSM8K、CRUXEval、MBPP、AIME、CorrectBench和TruthfulQA等多个推理与诊断基准上，使用Llama-3和Qwen-3（8B）进行测试，显式调节结构使错误诊断能力显著提升，成功自纠正率提高三倍。对580组查询的盲评显示，84%的人类评价更青睐其可信度与元认知自知性，优于标准方法和思维链基线。将大模型推理扎根于成熟认知理论，为构建更透明、可诊断的AI系统提供了原则性路径。
原文摘要 · Abstract (English)
Large Language Models (LLMs) demonstrate strong reasoning performance, yet their ability to reliably monitor, diagnose, and correct their own errors remains limited. We introduce a psychologically grounded metacognitive framework that operationalizes Ann Brown's regulatory cycle (Planning, Monitoring, and Evaluation) as a structured prompting architecture, and study its integration within a lightweight dual-process MetaController for adaptive effort allocation. Across diverse reasoning and diagnostic benchmarks (GSM8K, CRUXEval, MBPP, AIME, CorrectBench, and TruthfulQA) using Llama-3 and Qwen-3 (8B), explicit regulatory structuring substantially improves error diagnosis and yields a threefold increase in successful self-correction. Blinded human evaluations over 580 query pairs show an 84% aggregate preference for trustworthiness and metacognitive self-awareness over standard and Chain-of-Thought baselines. Grounding LLM reasoning in established cognitive theory offers a principled path toward more transparent and diagnostically robust AI systems.
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。