From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users
For developers of conversational AI systems, this work addresses the overlooked influence of user personality on empathy in long-term interactions, though it is an incremental extension of existing empathy research.
The paper introduces the task of personalized empathy for LLMs, adapting empathetic strategies to individual users' personality traits from long-term interactions. The proposed PereGRM framework achieves consistent performance improvements across settings, demonstrating effectiveness for enhancing personalized empathy.
As Large Language Models (LLMs) are increasingly deployed in long-term interactions with users, empathy has become an increasingly important capability. However, existing research overlooks the influence of users' personality traits on empathetic strategies during long-term interactions. To address this gap, we introduce the task of personalized empathy, which focuses on adapting empathetic strategies according to users' personalized characteristics derived from history. To study and enhance this capability, we construct PersonaEmp, a personalized empathy dataset built from long-term user-AI interactions, featuring rich user histories, persona information, and empathy-seeking queries. We further propose PereGRM, a reward modeling framework that combines the empathy evaluation structure with dynamic evaluation criteria generation for fine-grained reward modeling. Experimental results across different settings and multiple judge models show that PereGRM consistently achieves the strongest performance improvements, indicating its effectiveness for enhancing personalized empathetic capabilities.