Emotional Support with LLM-based Empathetic Dialogue Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909955656777728 |
|---|---|
| author | Wang, Shiquan Fang, Ruiyu He, Zhongjiang Song, Shuangyong Li, Yongxiang |
| author_facet | Wang, Shiquan Fang, Ruiyu He, Zhongjiang Song, Shuangyong Li, Yongxiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12820 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Emotional Support with LLM-based Empathetic Dialogue Generation Wang, Shiquan Fang, Ruiyu He, Zhongjiang Song, Shuangyong Li, Yongxiang Artificial Intelligence Computation and Language 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. |
| title | Emotional Support with LLM-based Empathetic Dialogue Generation |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2507.12820 |