The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation

TL;DR

This paper introduces the Socratic Inquiry Framework (SIF), a modular approach that enables large language models to generate proactive, theory-grounded therapeutic questions, shifting from reactive responses to active cognitive guidance in therapy conversations.

Contribution

We propose SIF, a novel framework that decouples question timing and content, along with Socratic-QA dataset, to improve LLMs' proactive questioning in therapy settings without retraining.

Findings

SIF increases proactive questioning frequency.

SIF enhances conversational depth and therapeutic alignment.

Models demonstrate improved guidance over baseline responses.

Abstract

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.