APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation
Open Access
- 21 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 900-909
Abstract
Empathetic response generation is designed to comprehend the emotions of others and select the most appropriate strategies to assist them in resolving emotional challenges. Empathy can be categorized into cognitive empathy and affective empathy. The former pertains to the ability to understand and discern the emotional issues and situations of others, while the latter involves the capacity to provide comfort. To enhance one's empathetic abilities, it is essential to develop both these aspects. Therefore, we develop an innovative framework that combines retrieval augmentation and emotional support strategy integration. Our framework starts with the introduction of a comprehensive emotional palette for empathy. We then apply appraisal theory to decompose this palette and create a database of empathetic responses. This database serves as an external resource and enhances the LLM's empathy by integrating semantic retrieval mechanisms. Moreover, our framework places a strong emphasis on the proper articulation of response strategies. By incorporating emotional support strategies, we aim to enrich the model's capabilities in both cognitive and affective empathy, leading to a more nuanced and comprehensive empathetic response. Finally, we extract datasets ED and ET from the empathetic dialogue dataset EmpatheticDialogues and ExTES based on dialogue length. Experiments demonstrate that our framework can enhance the empathy ability of LLMs from both cognitive and affective empathy perspectives. Our code is released at https://github.com/CAS-SIAT-XinHai/APTNESS.Keywords
All Related Versions
Funding Information
- Shenzhen Science and Technology Innovation Program (KQTD20190929172835662)
- China Postdoctoral Science Foundation (2023M733654)
- National Natural Science Foundation of China (Grant No. 62376262)
- Guangdong Basic and Applied Basic Research Foundation (2023A1515110496)
- the Natural Science Foundation of Guangdong province of China (2024A1515030166)
This publication has 11 references indexed in Scilit:
- Generative Relevance Feedback with Large Language Models2023
- Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models2023
- CEM: Commonsense-Aware Empathetic Response GenerationProceedings of the AAAI Conference on Artificial Intelligence, 2022
- (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge GraphsProceedings of the AAAI Conference on Artificial Intelligence, 2021
- ConceptNet 5.5: An Open Multilingual Graph of General KnowledgeProceedings of the AAAI Conference on Artificial Intelligence, 2017
- From what isn’t Empathy to Empathic Learning ProcessProcedia - Social and Behavioral Sciences, 2014
- The QCAE: A Questionnaire of Cognitive and Affective EmpathyJournal of Personality Assessment, 2011
- Noise Reduction in Speech Processing2009
- Cognitive Empathy and Emotional Empathy in Human Behavior and EvolutionThe Psychological Record, 2006
- Number of Scale Points and the Reliability of ScalesEducational and Psychological Measurement, 1965