cs.AI updates on arXiv.org 前天 19:10
Dynamic Context Adaptation for Consistent Role-Playing Agents with Retrieval-Augmented Generations
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出AMADEUS,一种结合自适应文本分割、引导选择和属性提取的角色扮演数据集,有效模拟角色知识及个性。

arXiv:2508.02016v1 Announce Type: new Abstract: We propose AMADEUS, which is composed of Adaptive Context-aware Text Splitter (ACTS), Guided Selection (GS), and Attribute Extractor (AE). ACTS finds an optimal chunk length and hierarchical contexts for each character. AE identifies a character's general attributes from the chunks retrieved by GS and uses these attributes as a final context to maintain robust persona consistency even when answering out of knowledge questions. To facilitate the development and evaluation of RAG-based RPAs, we construct CharacterRAG, a role-playing dataset that consists of persona documents for 15 distinct fictional characters totaling 976K written characters, and 450 question and answer pairs. We find that our framework effectively models not only the knowledge possessed by characters, but also various attributes such as personality.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

AMADEUS 角色扮演 文本分割 数据集 个性模拟
相关文章