arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2406.01171cs.CL

大语言模型中角色设定的双重叙事:角色扮演与个性化研究综述

Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization

National Taiwan University(台湾大学);Academia Sinica(中央研究院);University of Virginia(弗吉尼亚大学)

Yu-Min Tseng, Yu-Chao Huang, Teng-Yun Hsiao, Wei-Lin Chen, Chao-Wei Huang, Yu Meng, Yun-Nung Chen

AI总结:

该综述针对大语言模型(LLM)中角色设定研究零散无系统分类的问题,将相关研究划分为LLM角色扮演与LLM个性化两大方向,介绍了LLM性格评估方法,是首篇从角色设定统一视角开展的综述,并维护了相关论文集合。

摘要:

角色设定(persona)概念最初应用于对话研究领域,如今已重新成为适配大语言模型(LLM)特定场景(如个性化搜索、LLM 作为评审)的颇具前景的框架。然而,当前围绕 LLM 中角色设定应用的研究较为零散,缺乏系统的分类体系。为填补这一空白,本文开展了全面综述,对该领域的研究现状进行分类。我们梳理出两大研究方向:一是 LLM 角色扮演,即为 LLM 分配角色设定;二是 LLM 个性化,即 LLM 适配用户角色设定。此外,本文还介绍了现有的 LLM 性格评估方法。据我们所知,这是首篇从角色设定统一视角综述 LLM 角色扮演与个性化研究的工作。我们持续维护相关论文集合,以推动未来研究:https://github.com/MiuLab/PersonaLLM-Survey

英文摘要:

The concept of persona, originally adopted in dialogue literature, has re-surged as a promising framework for tailoring large language models (LLMs) to specific context (e.g., personalized search, LLM-as-a-judge). However, the growing research on leveraging persona in LLMs is relatively disorganized and lacks a systematic taxonomy. To close the gap, we present a comprehensive survey to categorize the current state of the field. We identify two lines of research, namely (1) LLM Role-Playing, where personas are assigned to LLMs, and (2) LLM Personalization, where LLMs take care of user personas. Additionally, we introduce existing methods for LLM personality evaluation. To the best of our knowledge, we present the first survey for role-playing and personalization in LLMs under the unified view of persona. We continuously maintain a paper collection to foster future endeavors: https://github.com/MiuLab/PersonaLLM-Survey

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑