PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling

• URL: http://arxiv.org/abs/2601.12392v1
• Date: Sun, 18 Jan 2026 13:06:13 GMT
• Title: PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
• Abstract summary: We propose PsychChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling.<n> Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module and Risk Control Module.<n>The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline.
• Score: 12.348236978084671
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated notable advancements in psychological counseling. However, existing models generally do not explicitly model seekers' emotion shifts across counseling sessions, a core focus in classical psychological schools. Moreover, how to align counselor models' responses with these emotion shifts while proactively mitigating safety risks remains underexplored. To bridge these gaps, we propose PsychēChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling. Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module, to capture seekers' current emotions and emotion shifts; and Risk Control Module, to anticipate seekers' subsequent reactions and identify potential risks. Furthermore, we introduce two modeling paradigms. The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline. The LLM Mode integrates these stages into a unified chain-of-thought for end-to-end inference, balancing efficiency and performance. Extensive experiments, including interactive scoring, dialogue-level evaluation, and human assessment, demonstrate that PsychēChat outperforms existing methods for emotional insight and safety control.

Related papers

• EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation [10.967647558354725]
  EmoTrace is a multi-turn dialogue corpus generation framework centered on modeling seekers' emotional trajectories.<n>We construct seekers' cognitive profile and introduce a seeker module with emotional schemas and an associated activation mechanism, a counselor module, and an emotional trajectory control module.<n> Experimental results demonstrate that the proposed method outperforms existing approaches in terms of emotional richness and empathy quality.
  arXiv  Detail & Related papers  (2026-07-26T13:30:04Z)
• From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue [4.64388134104662]
  We propose a CPM-grounded emotion evolution multi-agent framework for supporting emotional changes in persona-based dialogue.<n>Instead of treating a character's emotion as a fixed attribute, CPM-MultiAgent represents it as a latent state that is continuously reshaped by dialogue triggers.
  arXiv  Detail & Related papers  (2026-07-08T18:06:03Z)
• Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts [16.938835302814084]
  We develop a persona-conditioned user simulator capable of engaging in multi-turn dialogue with psychological personas and staged emotional pacing.<n>We identify several common failure patterns, including affective misalignments, ethical failures, and cross-dimensional trade-offs where empathy supersedes responsibility.
  arXiv  Detail & Related papers  (2026-04-03T04:10:46Z)
• How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study [33.5007842598689]
  We investigate whether emotional signals can shape the behavior of large language models (LLMs) and agents.<n>Existing emotion-aware studies mainly treat emotion as a surface-level style factor or a perception target.<n>We propose E-STEER, an interpretable emotion steering framework that enables direct representation-level intervention.
  arXiv  Detail & Related papers  (2026-03-09T12:20:02Z)
• DELTA: Deliberative Multi-Agent Reasoning with Reinforcement Learning for Multimodal Psychological Counseling [13.005090874995645]
  We introduce DELTA, a multi-agent framework that models counseling as a structured reasoning process over multimodal signals.<n>We show that DELTA improves both counseling quality and emotion across models.
  arXiv  Detail & Related papers  (2026-02-04T00:56:05Z)
• A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction [50.05919688888947]
  This paper presents a unified spoken language model for emotional intelligence, enhanced by a novel data construction strategy termed Injected Emotional-Attribution Thinking (IEAT)<n>IEAT incorporates user emotional states and their underlying causes into the model's internal reasoning process, enabling emotion-aware reasoning to be internalized rather than treated as explicit supervision.<n> Experiments on the Human-like Spoken Dialogue Systems Challenge (HumDial) Emotional Intelligence benchmark demonstrate that the proposed approach achieves top-ranked performance across emotional trajectory modeling, emotional reasoning, and empathetic response generation.
  arXiv  Detail & Related papers  (2026-01-08T14:07:30Z)
• Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language Models [6.810484095299127]
  Emotional support is a core capability in human-AI interaction, with applications including psychological counseling, role play, and companionship.<n>Existing evaluations of large language models (LLMs) often rely on short, static dialogues and fail to capture the dynamic and long-term nature of emotional support.<n>Our framework constructs a large-scale benchmark consisting of 328 emotional contexts and 1,152 disturbance events, simulating realistic emotional shifts under evolving dialogue scenarios.
  arXiv  Detail & Related papers  (2025-11-12T05:47:28Z)
• Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models [75.85319609088354]
  Sentient Agent as a Judge (SAGE) is an evaluation framework for large language models.<n>SAGE instantiates a Sentient Agent that simulates human-like emotional changes and inner thoughts during interaction.<n>SAGE provides a principled, scalable and interpretable tool for tracking progress toward genuinely empathetic and socially adept language agents.
  arXiv  Detail & Related papers  (2025-05-01T19:06:10Z)
• From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models [16.350658746140788]
  Large language models (LLMs) struggle to express emotions in a consistent, controllable, and contextually appropriate manner.<n>We propose a controllable emotion generation framework based on Emotion Vectors (EVs)<n>Our method enables fine-grained, continuous modulation of emotional tone without any additional training or architectural modification.
  arXiv  Detail & Related papers  (2025-02-06T13:38:57Z)
• EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics [12.105216351739422]
  EmoDynamiX models the discourse dynamics between user fine-grained emotions and system strategies using a heterogeneous graph for better performance and transparency.<n> Experimental results on two ESC datasets show EmoDynamiX outperforms previous state-of-the-art methods with a significant margin.
  arXiv  Detail & Related papers  (2024-08-16T14:54:41Z)
• Self-Emotion Blended Dialogue Generation in Social Simulation Agents [18.781929161272853]
  This study explores how self-emotion affects the agents' behaviors in dialogue strategies and decision-making within a large language model (LLM)-driven simulation framework. The results show that incorporating self-emotion helps agents exhibit more human-like dialogue strategies. In a virtual simulation environment where agents have discussions on multiple topics, we show that self-emotion of agents can significantly influence the decision-making process of the agents.
  arXiv  Detail & Related papers  (2024-08-03T02:11:48Z)
• CauESC: A Causal Aware Model for Emotional Support Conversation [79.4451588204647]
  Existing approaches ignore the emotion causes of the distress. They focus on the seeker's own mental state rather than the emotional dynamics during interaction between speakers. We propose a novel framework CauESC, which firstly recognizes the emotion causes of the distress, as well as the emotion effects triggered by the causes.
  arXiv  Detail & Related papers  (2024-01-31T11:30:24Z)
• Dynamic Causal Disentanglement Model for Dialogue Emotion Detection [77.96255121683011]
  We propose a Dynamic Causal Disentanglement Model based on hidden variable separation. This model effectively decomposes the content of dialogues and investigates the temporal accumulation of emotions. Specifically, we propose a dynamic temporal disentanglement model to infer the propagation of utterances and hidden variables.
  arXiv  Detail & Related papers  (2023-09-13T12:58:09Z)
• Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection [47.60224978460442]
  We propose a Serial and Emotion-Knowledge interaction (SEEK) method for empathetic dialogue generation. We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response. Besides, we design a novel framework to model the interaction between knowledge and emotion to generate more sensible response.
  arXiv  Detail & Related papers  (2022-10-21T03:51:18Z)
• Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction [55.47134146639492]
  This article proposes a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post. Experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness.
  arXiv  Detail & Related papers  (2021-06-06T06:26:15Z)

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.