Lune

EMNLP Findings2025

CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling

Mingyu Chen, Jingkai Lin, Zhaojie Chu, Xiaofen Xing, Yirong Chen, Xiangmin Xu

Abstract

Recently, advancements in AI counseling based on large language models have shown significant progress. However, existing studies employ a one-time generation approach to synthesize multi-turn dialogue samples, resulting in low therapy fidelity and failing to capture the decision-making rationale behind each response. In this work, we propose CATCH, a novel data synthesis framework designed to address these challenges. Specifically, to improve therapy fidelity, we introduce the Progressive Dialogue Synthesis strategy, which extracts goals, resources, and solutions from a client's self-report, organizes them into structured outlines, and then incrementally generates stage-aligned counseling dialogues. To capture decision-making rationale behind each response, we propose the Memory-Driven Dynamic Planning thinking pattern that integrates memory enhancement, global planning, and strategy reasoning; a collaborative multi-agent optimizer then leverages MDP to attach explicit chain-of-thought to each dialogue turn. Extensive experiments and human evaluations demonstrate that CATCH significantly enhances fidelity and logical coherence in AI counseling. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling cites SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations
  • Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory cites SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support
  • SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations cites LoRA: Low-Rank Adaptation of Large Language Models
  • SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations cites SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support
  • SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support cites LoRA: Low-Rank Adaptation of Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on6

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy ConversationsYirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng et al.EMNLP Findings 2023 · 81 citations
  3. SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health SupportHuachuan Qiu, Hongliang He, Shuai Zhang, Anqi Li et al.EMNLP Findings 2024 · 51 citations
  4. PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological CounselingHaojie Xie, Yirong Chen, Xiaofen Xing, Jingkai Lin et al.ACL 2025 · 43 citations
  5. Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral TheorySuyeon Lee, Sunghwan Kim, Minju Kim, Dongjin Kang et al.EMNLP Findings 2024 · 14 citations

Related papers

  1. MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing CounselingYizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang et al.ACL Findings 2026
  2. Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing SystemsJie Zeng, Yukiko I. NakanoACL Findings 2026 · 1 citation
  3. CFlowPsyD: An Analysis-Enhanced Dataset for Asynchronous Psychological Counseling through Self-Optimizing Multi-Agent FrameworkDonghao Li, Yifan Deng, Jinta Weng, Xingsheng Zhang et al.ACL Findings 2026
  4. Psychological Counseling Cannot Be Achieved Overnight: Automated Psychological Counseling Through Multi-Session ConversationsBichen Wang, Junzhe Wang, Yixin Sun, Xing Fu et al.ACL Findings 2026
  5. PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling DialoguesYi Feng, Zijie Yang, Chen Zhang, Wenxuan Zhang et al.ACL Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines