# You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations

Source: [You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations](<https://www.sota2.com/research/paper/69438aa2423ea422657295a0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-19T05:00:11.482Z

Authors: Hongbin Na, Zimu Wang, Zhaoming Chen, Peilin Zhou, Yining Hua, Grace Ziqi Zhou, Haiyang Zhang, Tao Shen, Wei Wang, John Torous, Shaoxiong Ji, Ling Chen

Published: 2025-12-17T17:11:05.000Z

## Abstract

Psychological defenses are strategies, often automatic, that people use to manage distress. Rigid or overuse of defenses is negatively linked to mental health and shapes what speakers disclose and how they accept or resist help. However, defenses are complex and difficult to reliably measure, particularly in clinical dialogues. We introduce PsyDefConv, a dialogue corpus with help seeker utterances labeled for defense level, and DMRS Co-Pilot, a four-stage pipeline that provides evidence-based pre-annotations. The corpus contains 200 dialogues and 4709 utterances, including 2336 help seeker turns, with labeling and Cohen's kappa 0.639. In a counterbalanced study, the co-pilot reduced average annotation time by 22.4%. In expert review, it averaged 4.62 for evidence, 4.44 for clinical plausibility, and 4.40 for insight on a seven-point scale. Benchmarks with strong language models in zero-shot and fine-tuning settings demonstrate clear headroom, with the best macro F1-score around 30% and a tendency to overpredict mature defenses. Corpus analyses confirm that mature defenses are most common and reveal emotion-specific deviations. We will release the corpus, annotations, code, and prompts to support research on defensive functioning in language.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Psychological defense mechanism classification on PsyDefDetect classes 1-8 (hidden test)](<https://www.sota2.com/research/sota/psychological-defense-mechanism-classification-on-psydefdetect-classes-1-8-hidden-test.md>): Psychological defense mechanism classification; PsyDefDetect classes 1-8 (hidden test); Macro F1 Score: 31.5.

- [Psychological defense mechanism classification on PSYDEFCONV (test)](<https://www.sota2.com/research/sota/psychological-defense-mechanism-classification-on-psydefconv-test.md>): Psychological defense mechanism classification; PSYDEFCONV (test); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.15601>)

[PDF](<https://arxiv.org/pdf/2512.15601.pdf>)
