TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM
This work addresses the challenge of improving empathetic response generation in AI systems for conversational agents, though it appears incremental as it builds on existing knowledge bases and tool learning methods.
The authors tackled the problem of generating empathetic responses in conversations by proposing the Emotional Knowledge Tool Calling (EKTC) framework, which uses tool learning to flexibly integrate external commonsense knowledge, and they validated it on the EMPATHETIC DIALOGUE dataset, showing effective enhancement in LLM performance.
Empathetic conversation is a crucial characteristic in daily conversations between individuals. Nowadays, Large Language models (LLMs) have shown outstanding performance in generating empathetic responses. Knowledge bases like COMET can assist LLMs in mitigating illusions and enhancing the understanding of users' intentions and emotions. However, models remain heavily reliant on fixed knowledge bases and unrestricted incorporation of external knowledge can introduce noise. Tool learning is a flexible end-to-end approach that assists LLMs in handling complex problems. In this paper, we propose Emotional Knowledge Tool Calling (EKTC) framework, which encapsulates the commonsense knowledge bases as empathetic tools, enabling LLMs to integrate external knowledge flexibly through tool calling. In order to adapt the models to the new task, we construct a novel dataset TOOL-ED based on the EMPATHETICMPATHETIC DIALOGUE (ED) dataset. We validate EKTC on the ED dataset, and the experimental results demonstrate that our framework can enhance the ability of LLMs to generate empathetic responses effectively.