Know Thyself, Know Thy User: Dual-Perspective Reasoning Architecture for Role-Playing Language Models

Haotong Sun

Keywords: role-playing language models, axial attention, dual-perspective reasoning, mixture of experts, self-awareness

TL;DR: KSKT realizes "know thyself, know thy user" via dual-perspective reasoning architecture for role-playing LLMs, achieving balanced self/other awareness and 6.4% performance gains.

Abstract: Current role-playing Large Language Models (LLMs) face a fundamental challenge: balancing character authenticity with user satisfaction. While recent dual-process and dual-perspective approaches have made progress, existing systems still struggle with role-user conflicts where character constraints clash with user expectations. We introduce the KnowSelf-KnowOther Transformer (KSKT), a novel dual-perspective reasoning architecture that addresses this challenge through four integrated innovations: Dual-Stream Axial Attention that processes self-understanding and other-understanding along functionally decoupled dimensions, Bipolar Reasoning combining fast intuitive and slow deliberative pathways, Mutual-Understanding Position Encoding capturing dynamic relational contexts, and Self-Awareness Mixture of Experts specializing in multi-dimensional character comprehension. Unlike previous approaches that treat dual-perspective reasoning as post-hoc optimization or separate modules, KSKT integrates mutual understanding directly into the model architecture. Extensive experiments on CharacterBench demonstrate significant improvements: 6.4% overall enhancement over strong baselines, with particularly notable gains in persona consistency (8.7%) and emotional intelligence (15.2%). Critically, controlled experiments show KSKT maintains balanced dual-perspective reasoning (0.87 self-awareness, 0.87 other-awareness) in role-user conflict scenarios, while baseline models exhibit severe single-perspective bias (0.17 vs. 0.83). These results establish KSKT as an effective architectural framework for role-playing systems that must balance character authenticity with user engagement.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 17644