ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification
This work addresses the challenge of making psychotherapy more accessible by improving LLM accuracy for cognitive distortion classification, though it appears incremental as it builds on existing methods with added modules.
The authors tackled the problem of improving LLM-based classification of cognitive distortions in psychotherapy by proposing ERD, a framework that extracts relevant parts and uses multi-agent debate for reasoning, resulting in enhanced multi-class F1 and binary specificity scores on a public dataset.
Improving the accessibility of psychotherapy with the aid of Large Language Models (LLMs) is garnering a significant attention in recent years. Recognizing cognitive distortions from the interviewee's utterances can be an essential part of psychotherapy, especially for cognitive behavioral therapy. In this paper, we propose ERD, which improves LLM-based cognitive distortion classification performance with the aid of additional modules of (1) extracting the parts related to cognitive distortion, and (2) debating the reasoning steps by multiple agents. Our experimental results on a public dataset show that ERD improves the multi-class F1 score as well as binary specificity score. Regarding the latter score, it turns out that our method is effective in debiasing the baseline method which has high false positive rate, especially when the summary of multi-agent debate is provided to LLMs.