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

• URL: http://arxiv.org/abs/2602.01598v1
• Date: Mon, 02 Feb 2026 03:40:11 GMT
• Title: The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation
• Authors: Mingwen Zhang, Minqiang Yang, Changsheng Ma, Yang Yu, Hui Bai, Chen Xu, Xiangzhen Kong, Bin Hu,
• Abstract summary: We propose the textbfSocratic Inquiry Framework (SIF), a therapeutic intent planner that transforms psychological large language models.<n>SIF decouples textbfwhen to ask from textbfwhat to ask, enabling context-aware, theory-grounded questioning.<n> Experiments show that SIF significantly enhances proactive questioning frequency, conversational depth, and therapeutic alignment.
• Score: 10.636413819138319
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering [64.62317305868264]
  We present textbfKBQA-R1, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning.<n>Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions.<n>Experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-10T17:45:42Z)
• Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts [4.618735978506653]
  ROME is a novel framework that explicitly injects psychological knowledge into personality detection.<n>We show that ROME consistently outperforms state-of-the-art baselines in experiments on two real-world datasets.
  arXiv  Detail & Related papers  (2025-12-09T17:07:54Z)
• CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy [67.23830698947637]
  We propose a new benchmark, CBT-BENCH, for the systematic evaluation of cognitive behavioral therapy (CBT) assistance.<n>We include three levels of tasks in CBT-BENCH: I: Basic CBT knowledge acquisition, with the task of multiple-choice questions; II: Cognitive model understanding, with the tasks of cognitive distortion classification, primary core belief classification, and fine-grained core belief classification; III: Therapeutic response generation, with the task of generating responses to patient speech in CBT therapy sessions.<n> Experimental results indicate that while LLMs perform well in reciting CBT knowledge, they fall short in complex real-world scenarios
  arXiv  Detail & Related papers  (2024-10-17T04:52:57Z)
• Selective Prompting Tuning for Personalized Conversations with LLMs [31.28284591597932]
  We propose textbfSelective textbfPrompt textbfTuning (SPT), which softly prompts large language models (LLMs) for personalized conversations in a selective way. SPT significantly enhances response diversity by up to 90%, along with improvements in other critical performance indicators.
  arXiv  Detail & Related papers  (2024-06-26T09:03:52Z)
• On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation [47.35777964373532]
  Hallucination occurs when large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation.<n>Previous learning-based methods attempt to finetune models but are limited by off-policy sampling and coarse-grained feedback.<n>We present RLFH, an on-policy self-alignment approach that enables LLMs to actively explore their knowledge boundaries and self-correct generation behavior.
  arXiv  Detail & Related papers  (2024-06-18T02:43:49Z)
• LLM Questionnaire Completion for Automatic Psychiatric Assessment [49.1574468325115]
  We employ a Large Language Model (LLM) to convert unstructured psychological interviews into structured questionnaires spanning various psychiatric and personality domains. The obtained answers are coded as features, which are used to predict standardized psychiatric measures of depression (PHQ-8) and PTSD (PCL-C)
  arXiv  Detail & Related papers  (2024-06-09T09:03:11Z)
• Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach [55.613461060997004]
  Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks. We propose an innovative textitmetacognitive approach, dubbed textbfCLEAR, to equip LLMs with capabilities for self-aware error identification and correction.
  arXiv  Detail & Related papers  (2024-03-08T19:18:53Z)
• Socratic Reasoning Improves Positive Text Rewriting [49.32560132826547]
  Reframing a negative into a positive thought is at the crux of several cognitive approaches to mental health and psychotherapy.<n>We develop a novel framework called textscSocraticReframe to rationalize the thought rewriting process.
  arXiv  Detail & Related papers  (2024-03-05T15:05:06Z)
• Response Generation for Cognitive Behavioral Therapy with Large Language Models: Comparative Study with Socratic Questioning [6.400704401007114]
  This study investigates the impact of generated responses on subjective evaluations such as mood change, cognitive change, and dialogue quality. When using GPT-4, the amount of mood change, empathy, and other dialogue qualities improve significantly.
  arXiv  Detail & Related papers  (2024-01-29T08:53:41Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)
• Response-act Guided Reinforced Dialogue Generation for Mental Health Counseling [25.524804770124145]
  We present READER, a dialogue-act guided response generator for mental health counseling conversations. READER is built on transformer to jointly predict a potential dialogue-act d(t+1) for the next utterance (aka response-act) and to generate an appropriate response u(t+1) We evaluate READER on HOPE, a benchmark counseling conversation dataset.
  arXiv  Detail & Related papers  (2023-01-30T08:53:35Z)
• MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation [64.37111498077866]
  We propose a novel model for emotional support conversation. It infers the user's fine-grained emotional status, and then responds skillfully using a mixture of strategy. Experimental results on the benchmark dataset demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2022-03-25T10:32:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.