mlsanityData to 14 Oct 2026

Emotional Support with LLM-based Empathetic Dialogue Generation

arXiv 2507.12820 ↗First posted 17 Jul 2025cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Emotional Support Conversation (ESC) aims to provide empathetic and effective emotional assistance through dialogue, addressing the growing demand for mental health support. This paper presents our solution for the NLPCC 2025 Task 8 ESC evaluation, where we leverage large-scale language models enhanced by prompt engineering and finetuning techniques. We explore both parameter-efficient Low-Rank Adaptation and full-parameter fine-tuning strategies to improve the model's ability to generate supportive and contextually appropriate responses. Our best model ranked second in the competition, highlighting the potential of combining LLMs with effective adaptation methods for ESC tasks. Future work will focus on further enhancing emotional understanding and response personalization to build more practical and reliable emotional support systems.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 17 Jul 2025.

Builds on

24 of 47 references.

References · 24

  1. 2021Towards Emotional Support Dialog Systemscited by 299
  2. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  3. 2025Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Modelcited by 55
  4. 2024AI Flow at the Network Edgecited by 46
  5. 2022PAL: Persona-Augmented Emotional Support Conversation Generationcited by 39
  6. 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 37
  7. 2023TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transitioncited by 30
  8. 2024Towards Multimodal Emotional Support Conversation Systemscited by 23
  9. 2024Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Mergingcited by 16
  10. 2023Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approachcited by 15
  11. 2024TeleChat Technical Reportcited by 15
  12. 2024Tele-FLM Technical Reportcited by 12
12 more
  1. 2023Knowledge-enhanced Memory Model for Emotional Support Conversationcited by 7
  2. 2020MLR: A Two-stage Conversational Query Rewriting Model with Multi-task Learningcited by 6
  3. 2022An Empathetic AI Coach for Self-Attachment Therapycited by 5
  4. 2024Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversationcited by 5
  5. 2015Detecting Concept-level Emotion Cause in Microbloggingcited by 4
  6. 2024CauESC: A Causal Aware Model for Emotional Support Conversationcited by 4
  7. 2015Classifying and Ranking Microblogging Hashtags with News Categoriescited by 3
  8. 2020TCNN: Triple Convolutional Neural Network Models for Retrieval-based Question Answering System in E-commercecited by 3
  9. 2024Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximizationcited by 3
  10. 2025EmoFSM: A Finite State Machine for Emotional Support Conversationcited by 3
  11. 2021An Emotion-controlled Dialog Response Generation Model with Dynamic Vocabularycited by 2
  12. 2023Mining Interest Trends and Adaptively Assigning SampleWeight for Session-based Recommendationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethicscited by 4
  2. 2025First, Do No Harm: AI Supervisor Scaffolds Novice Growth in Counselor Educationcited by 0
  3. 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challengescited by 0
  4. 2026From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Healthcited by 0