Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.01598 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912868169940992 |
|---|---|
| author | Zhang, Mingwen Yang, Minqiang Ma, Changsheng Yu, Yang Bai, Hui Xu, Chen Kong, Xiangzhen Hu, Bin |
| author_facet | Zhang, Mingwen Yang, Minqiang Ma, Changsheng Yu, Yang Bai, Hui Xu, Chen Kong, Xiangzhen Hu, Bin |
| contents | Proactive questioning, where therapists deliberately initiate structured, cognition-guiding inquiries, is a cornerstone of cognitive behavioral therapy (CBT). Yet, current psychological large language models (LLMs) remain overwhelmingly reactive, defaulting to empathetic but superficial responses that fail to surface latent beliefs or guide behavioral change. To bridge this gap, we propose the \textbf{Socratic Inquiry Framework (SIF)}, a lightweight, plug-and-play therapeutic intent planner that transforms LLMs from passive listeners into active cognitive guides. SIF decouples \textbf{when to ask} (via Strategy Anchoring) from \textbf{what to ask} (via Template Retrieval), enabling context-aware, theory-grounded questioning without end-to-end retraining. Complementing SIF, we introduce \textbf{Socratic-QA}, a high-quality dataset of strategy-aligned Socratic sequences that provides explicit supervision for proactive reasoning. Experiments show that SIF significantly enhances proactive questioning frequency, conversational depth, and therapeutic alignment, marking a clear shift from reactive comfort to proactive exploration. Our work establishes a new paradigm for psychologically informed LLMs: not just to respond, but to guide. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01598 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation Zhang, Mingwen Yang, Minqiang Ma, Changsheng Yu, Yang Bai, Hui Xu, Chen Kong, Xiangzhen Hu, Bin Computation and Language Proactive questioning, where therapists deliberately initiate structured, cognition-guiding inquiries, is a cornerstone of cognitive behavioral therapy (CBT). Yet, current psychological large language models (LLMs) remain overwhelmingly reactive, defaulting to empathetic but superficial responses that fail to surface latent beliefs or guide behavioral change. To bridge this gap, we propose the \textbf{Socratic Inquiry Framework (SIF)}, a lightweight, plug-and-play therapeutic intent planner that transforms LLMs from passive listeners into active cognitive guides. SIF decouples \textbf{when to ask} (via Strategy Anchoring) from \textbf{what to ask} (via Template Retrieval), enabling context-aware, theory-grounded questioning without end-to-end retraining. Complementing SIF, we introduce \textbf{Socratic-QA}, a high-quality dataset of strategy-aligned Socratic sequences that provides explicit supervision for proactive reasoning. Experiments show that SIF significantly enhances proactive questioning frequency, conversational depth, and therapeutic alignment, marking a clear shift from reactive comfort to proactive exploration. Our work establishes a new paradigm for psychologically informed LLMs: not just to respond, but to guide. |
| title | The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.01598 |