mlsanityData to 7 Oct 2026

From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations

arXiv 2502.11451 ↗First posted 17 Feb 2025cs.CLcited by 23

Not on the map. Why?

Abstract (arXiv)

The rapid advancement of Large Language Models (LLMs) has revolutionized the generation of emotional support conversations (ESC), offering scalable solutions with reduced costs and enhanced data privacy. This paper explores the role of personas in the creation of ESC by LLMs. Our research utilizes established psychological frameworks to measure and infuse persona traits into LLMs, which then generate dialogues in the emotional support scenario. We conduct extensive evaluations to understand the stability of persona traits in dialogues, examining shifts in traits post-generation and their impact on dialogue quality and strategy distribution. Experimental results reveal several notable findings: 1) LLMs can infer core persona traits, 2) subtle shifts in emotionality and extraversion occur, influencing the dialogue dynamics, and 3) the application of persona traits modifies the distribution of emotional support strategies, enhancing the relevance and empathetic quality of the responses. These findings highlight the potential of persona-driven LLMs in crafting more personalized, empathetic, and effective emotional support dialogues, which has significant implications for the future design of AI-driven emotional support systems.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 21 of its 80 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

21 of 80 references.

References · 21

  1. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  2. 2021Towards Emotional Support Dialog Systemscited by 294
  3. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  4. 2020A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Supportcited by 182
  5. 2021PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Supportcited by 92
  6. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
  7. 2022AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversationcited by 79
  8. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
  9. 2023CharacterChat: Learning towards Conversational AI with Personalized Social Supportcited by 58
  10. 2022Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversationcited by 56
  11. 2024Towards Human-centered Proactive Conversational Agentscited by 48
  12. 2024ESCoT: Towards Interpretable Emotional Support Dialogue Systemscited by 46
9 more
  1. 2024Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactionscited by 43
  2. 2023Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversationscited by 41
  3. 2022PAL: Persona-Augmented Emotional Support Conversation Generationcited by 39
  4. 2022CAMS: An Annotated Corpus for Causal Analysis of Mental Health Issues in Social Media Postscited by 34
  5. 2021Exploring Self-Identified Counseling Expertise in Online Support Forumscited by 10
  6. 2025Consistency of Responses and Continuations Generated by Large Language Models on Social Mediacited by 7
  7. 2023Affective Conversational Agents: Understanding Expectations and Personal Influencescited by 6
  8. 2024Is persona enough for personality? Using ChatGPT to reconstruct an agent's latent personality from simple descriptionscited by 5
  9. 2024Persona Extraction Through Semantic Similarity for Emotional Support Conversation Generationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 16.

23 papers.

Sort:

By area:

  1. 2025Efficient Inference for Large Reasoning Models: A Surveycited by 58
  2. 2025Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Modelscited by 21
  3. 2026Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISMcited by 9
  4. 2025Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inferencecited by 5
  5. 2026PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Modelscited by 5
  6. 2025Are LLM Agents Behaviorally Coherent? Latent Profiles for Social Simulationcited by 3
  7. 2025Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?cited by 3
  8. 2026MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Modelscited by 3
  9. 2025PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoningcited by 2
  10. 2026Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axescited by 2
  11. 2026Beyond Static Personas: Situational Personality Steering for Large Language Modelscited by 2
  12. 2025Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variationscited by 1
11 more
  1. 2026Stephanie2: Thinking, Waiting, and Making Decisions Like Humans in Step-by-Step AI Social Chatcited by 1
  2. 2026The Slow Drift of Support: Boundary Failures in Multi-Turn Mental Health LLM Dialoguescited by 1
  3. 2026PEMAND: Persona-Enriched Multi-Agent Negotiation for Household Decision-Makingcited by 0
  4. 2026From Chatbots to Confidants: A Cross-Cultural Study of LLM Adoption for Emotional Supportcited by 0
  5. 2026Enhancing Target-Guided Proactive Dialogue Systems via Conversational Scenario Modeling and Intent-Keyword Bridgingcited by 0
  6. 2026In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scorescited by 0
  7. 2026Creating Multilingual Mental Health Dialogue Datasets: Limits of Persona-Based Localization via Nationality and Languagecited by 0
  8. 2026Self-Stigma Is Not a Monolith, but Generic Empathy Is: Persona-Conditioned LLM Support for People Who Use Drugscited by 0
  9. 2026CCBENCH: Assessing LLM Cultural Competence via Implicitly Signaled Norms using Health Queriescited by 0
  10. 2026Emotional Labor Strategy Preferences in LLM Personascited by 0
  11. 2026EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidancecited by 0