Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference
This addresses the challenge of building more human-like and emotionally supportive chatbots for users, though it appears incremental as it builds on existing commonsense inference methods.
The paper tackles the problem of LLMs struggling to generate empathetic and supportive dialogue due to limited commonsense knowledge, and presents the Sibyl framework to enhance this by focusing on future dialogue context, resulting in comprehensive improvements in response quality.
Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in multi-turn conversations. Despite having access to commonsense knowledge to better understand the psychological aspects and causality of dialogue context, even these powerful LLMs struggle to achieve the goals of empathy and emotional support. Current commonsense knowledge derived from dialogue contexts is inherently limited and often fails to adequately anticipate the future course of a dialogue. This lack of foresight can mislead LLMs and hinder their ability to provide effective support. In response to this challenge, we present an innovative framework named Sensible and Visionary Commonsense Knowledge (Sibyl). Designed to concentrate on the immediately succeeding dialogue, this paradigm equips LLMs with the capability to uncover the implicit requirements of the conversation, aiming to elicit more empathetic responses. Experimental results demonstrate that incorporating our paradigm for acquiring commonsense knowledge into LLMs comprehensively enhances the quality of their responses.