Does "Reasoning" with Large Language Models Improve Recognizing, Generating, and Reframing Unhelpful Thoughts?
This addresses the challenge of enhancing Cognitive Behavioral Therapy (CBT) tools for mental health applications, though it is incremental as it builds on existing reasoning strategies.
The study tackled the problem of improving cognitive reframing in mental health using Large Language Models (LLMs) by testing reasoning methods like CoT and self-consistency, finding that these augmented methods consistently outperformed state-of-the-art pretrained reasoning models on tasks such as recognizing, generating, and reframing unhelpful thoughts.
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 We find that augmented reasoning methods, even when applied to "outdated" LLMs like GPT-3.5, consistently outperform state-of-the-art pretrained reasoning models on recognizing, generating and reframing unhelpful thoughts.