大语言模型的“推理”能力是否改善了识别、生成和重构无益想法？
Does "Reasoning" with Large Language Models Improve Recognizing, Generating, and Reframing Unhelpful Thoughts?
AI总结：
研究探讨了CoT和自洽性等增强推理策略在认知重构任务中的作用，发现其即使应用于GPT-3.5等旧模型，在识别、生成和重构无益想法上也优于最先进的预训练推理模型。
摘要：
认知重构是认知行为疗法（CBT）的核心要素，它通过寻找积极意义来帮助个体重新解释消极经历。大语言模型（LLMs）的最新进展表明，基于推理的策略能提升性能。这启发了一个有前景的方向：利用LLMs的推理能力，通过模拟批判性思维过程来改善CBT和心理重构，从而可能实现对认知扭曲更有效的识别、生成和重构。在本研究中，我们探讨了多种推理方法的作用，包括预训练推理LLMs以及CoT和自洽性等增强推理策略，以增强LLMs执行认知重构任务的能力。我们发现，增强推理方法即使应用于GPT-3.5等“过时”的LLMs，在识别、生成和重构无益想法方面也始终优于最先进的预训练推理模型。
英文摘要：
Cognitive Reframing, a core element of Cognitive Behavioral Therapy (CBT), helps individuals reinterpret negative experiences by finding positive meaning. Recent advances in Large Language Models (LLMs) have demonstrated improved performance through reasoning-based strategies. This inspires a promising direction of leveraging the reasoning capabilities of LLMs to improve CBT and mental reframing by simulating the process of critical thinking, potentially enabling more effective recognition, generation, and reframing of cognitive distortions. In this work, we investigate the role of various reasoning methods, including pre-trained reasoning LLMs and augmented reasoning strategies such as CoT and self-consistency in enhancing LLMs' ability to perform cognitive reframing tasks. We find that augmented reasoning methods, even when applied to "outdated" LLMs like GPT-3.5, consistently outperform state-of-the-art pretrained reasoning models on recognizing, generating and reframing unhelpful thoughts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
