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

arXiv: https://arxiv.org/abs/2512.15601 · HTML: https://mlsanity.com/paper/2512.15601/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation](https://mlsanity.com/paper/2202.13047/) (2022)
- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Building Emotional Support Chatbots in the Era of LLMs](https://mlsanity.com/paper/2308.11584/) (2023)
- [Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation](https://mlsanity.com/paper/2402.13211/) (2024)
- [ESCoT: Towards Interpretable Emotional Support Dialogue Systems](https://mlsanity.com/paper/2406.10960/) (2024)
- [SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent](https://mlsanity.com/paper/2412.08389/) (2024)
- [Detecting Conversational Mental Manipulation with Intent-Aware Prompting](https://mlsanity.com/paper/2412.08414/) (2024)
- [Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering](https://mlsanity.com/paper/2410.04752/) (2024)
- [Steering Conversational Large Language Models for Long Emotional Support Conversations](https://mlsanity.com/paper/2402.10453/) (2024)
- [MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses](https://mlsanity.com/paper/2509.17436/) (2025)
- [Emotional Supporters often Use Multiple Strategies in a Single Turn](https://mlsanity.com/paper/2505.15316/) (2025)

## Built on by (most cited first, 7 of 7)

- [N"urnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification](https://mlsanity.com/paper/2605.07606/) (2026)
- [Overview of the PsyDefDetect Shared Task at BioNLP 2026: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations](https://mlsanity.com/paper/2605.24907/) (2026)
- [UTS at PsyDefDetect: Multi-Agent Councils and Absence-Based Reasoning for Defense Mechanism Classification](https://mlsanity.com/paper/2605.09769/) (2026)
- [VISHC at PsyDefDetect: Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation](https://mlsanity.com/paper/2605.14380/) (2026)
- [LinguIUTics at PsyDefDetect: Iterative Imbalance-Aware Fine-tuning of Qwen3-8B for Psychological Defense Mechanism Classification](https://mlsanity.com/paper/2606.00647/) (2026)
- [SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue](https://mlsanity.com/paper/2609.01548/) (2026)
- [Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategies](https://mlsanity.com/paper/2609.20565/) (2026)

## Abstract (arXiv)

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.