Toward Real-World Chinese Psychological Support Dialogues: CPsDD Dataset and a Co-Evolving Multi-Agent System

• URL: http://arxiv.org/abs/2507.07509v1
• Date: Thu, 10 Jul 2025 07:56:35 GMT
• Title: Toward Real-World Chinese Psychological Support Dialogues: CPsDD Dataset and a Co-Evolving Multi-Agent System
• Authors: Yuanchen Shi, Longyin Zhang, Fang Kong,
• Abstract summary: We propose a framework that leverages limited real-world data and expert knowledge to fine-tune two large language models: Dialog Generator and Dialog.<n>The Generator creates large-scale psychological counseling dialogues based on predefined paths, which guide system response strategies and user interactions.<n>The Comprehensive Agent Dialogue Support System (CADSS), where a Profiler analyzes user characteristics, a Summarizer condenses dialogue history, a Planner selects strategies, and a Supporter generates empathetic responses.
• Score: 7.744725404359205
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The growing need for psychological support due to increasing pressures has exposed the scarcity of relevant datasets, particularly in non-English languages. To address this, we propose a framework that leverages limited real-world data and expert knowledge to fine-tune two large language models: Dialog Generator and Dialog Modifier. The Generator creates large-scale psychological counseling dialogues based on predefined paths, which guide system response strategies and user interactions, forming the basis for effective support. The Modifier refines these dialogues to align with real-world data quality. Through both automated and manual review, we construct the Chinese Psychological support Dialogue Dataset (CPsDD), containing 68K dialogues across 13 groups, 16 psychological problems, 13 causes, and 12 support focuses. Additionally, we introduce the Comprehensive Agent Dialogue Support System (CADSS), where a Profiler analyzes user characteristics, a Summarizer condenses dialogue history, a Planner selects strategies, and a Supporter generates empathetic responses. The experimental results of the Strategy Prediction and Emotional Support Conversation (ESC) tasks demonstrate that CADSS achieves state-of-the-art performance on both CPsDD and ESConv datasets.

Related papers

• DeepPsy-Agent: A Stage-Aware and Deep-Thinking Emotional Support Agent System [10.262822400879688]
  DeepPsy-Agent is an innovative psychological support system that combines the three-stage helping theory in psychology with deep learning techniques.<n>Based on 30,000 real psychological hotline conversations, we employ AI-simulated dialogues and expert re-annotation strategies to construct a high-quality multi-turn dialogue dataset.
  arXiv  Detail & Related papers  (2025-03-20T05:59:29Z)
• Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting [46.919537239016734]
  Large language models (LLMs) have simplified the implementation of multi-turn dialogues. It remains challenging to deliver satisfactory performance in low-resource domain, like psychological dialogue dialogue. We propose a knowledge-driven progressive thought prompting method to guide LLM to generate psychology-related dialogue.
  arXiv  Detail & Related papers  (2024-06-24T12:02:56Z)
• CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling [27.193022503592342]
  We propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues. A comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations.
  arXiv  Detail & Related papers  (2024-05-26T05:18:00Z)
• A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment [15.921295369286161]
  Data sparsity is the main challenge in building CS-based dialogue systems, particularly in the Chinese language. Making chit chat while providing emotional support is overlooked by the majority of existing cognitive dialogue systems. We propose a multi-source knowledge fusion method for CS dialogue (CSD), to generate open-ended responses guided by the CS principle and emotional support strategy.
  arXiv  Detail & Related papers  (2023-05-14T16:52:20Z)
• HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data [87.67278915655712]
  We present a new dialogue dataset, HybriDialogue, which consists of crowdsourced natural conversations grounded on both Wikipedia text and tables. The conversations are created through the decomposition of complex multihop questions into simple, realistic multiturn dialogue interactions.
  arXiv  Detail & Related papers  (2022-04-28T00:52:16Z)
• AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation [54.29029787836075]
  Crowdsourced dialogue corpora are usually limited in scale and topic coverage due to the expensive cost of data curation. In this work, we leverage large language models for dialogue augmentation in the task of emotional support conversation (ESC) We construct AugESC, an augmented dataset for the ESC task, which largely extends the scale and topic coverage of the crowdsourced ESConv corpus.
  arXiv  Detail & Related papers  (2022-02-26T03:17:08Z)
• Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations [15.230185998553159]
  We develop a novel dataset, named HOPE, to provide a platform for the dialogue-act classification in counselling conversations. We collect 12.9K utterances from publicly-available counselling session videos on YouTube, extract their transcripts, clean, and annotate them with DAC labels. We propose SPARTA, a transformer-based architecture with a novel speaker- and time-aware contextual learning for the dialogue-act classification.
  arXiv  Detail & Related papers  (2021-11-12T10:30:30Z)
• UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues [59.499965460525694]
  We propose a unified dialogue system (UniDS) with the two aforementioned skills. We design a unified dialogue data schema, compatible for both chit-chat and task-oriented dialogues. We train UniDS with mixed dialogue data from a pretrained chit-chat dialogue model.
  arXiv  Detail & Related papers  (2021-10-15T11:56:47Z)
• Is this Dialogue Coherent? Learning from Dialogue Acts and Entities [82.44143808977209]
  We create the Switchboard Coherence (SWBD-Coh) corpus, a dataset of human-human spoken dialogues annotated with turn coherence ratings. Our statistical analysis of the corpus indicates how turn coherence perception is affected by patterns of distribution of entities. We find that models combining both DA and entity information yield the best performances both for response selection and turn coherence rating.
  arXiv  Detail & Related papers  (2020-06-17T21:02:40Z)
• Rethinking Dialogue State Tracking with Reasoning [76.0991910623001]
  This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy for MultiWOZ 2.1.
  arXiv  Detail & Related papers  (2020-05-27T02:05:33Z)

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.