Can Large Language Models Assess and Reframe Psychological Attribution: A Benchmark and Analysis

Qiang Zhou, Hanzhen Zhu, Jiyang Liu, Pan Wang, Yufeng Tian, Rui Tu, Huaizhi Qu, Zhuoran Wang, Xin Hu, Lei Li, Tianlong Chen, Jingtong Hu

Keywords: Attributional reframing; Attributional Style; ASTD Benchmark

TL;DR: This paper introduces the Attributional Style Transfer Dataset (ASTD) and evaluation framework to assess and reframe psychological attributional styles using large language models for scalable mental health interventions.

Abstract:

According to the reformulated version of the Learned Helplessness theory, an individual who experiences uncontrollable negative events may subsequently develop a negative attributional style, thereby exhibiting greater susceptibility to depressive symptoms. This depressogenic attributional style not only contributes to depressive symptoms but also represents a malleable target for cognitive therapy.
Despite its theoretical and practical significance, computational research on attributional cognition remains underexplored due to the lack of large-scale, high-quality datasets and robust evaluation protocols. In this work, we introduce the Attributional Style Transfer Dataset (ASTD) along with dedicated evaluation metrics, the first benchmark designed to model, assess, and reframe attributional explanations at scale.
Constructed via a Prevent–Filter–Validate pipeline that integrates LLM-based generation with specialist validation, ASTD contains 42,000 real-world events paired with psychologically grounded attributions spanning seven styles. Using this dataset, we address two key challenges: (1) scalable assessment of attributional style via both supervised classifiers and zero/few-shot LLMs; and (2)attributional reframing and evaluation, where we propose automatic evaluation metrics to quantify psychological validity. Furthermore, we leverage our proposed metrics to construct a preference dataset, fine-tuning LLMs with Direct Preference Optimization (DPO) and achieving substantial gains in reframing quality. Together, our dataset, metrics, and methodology offer a new paradigm for understanding and modeling attributional style, with direct implications for scalable and adaptive mental health interventions.

Primary Area: datasets and benchmarks

Submission Number: 13471