Lune

EMNLP Findings2025

TailorRPA: A Retrieval-Based Framework for Eliciting Personalized and Coherent Role-Playing Agents in General Domain

Zhenpeng Gao, Xiaofen Xing, Xiangmin Xu

Abstract

Recent advancements of general domain oriented Role-playing Agents (RPAs) have enabled the agents to maintain character properties in a wide spectrum of daily tasks beyond mere scenario based chit-chatting. Nonetheless, current works lacks consideration of replicating internal properties of characters like finegrained memories, and failed to take account of aligning with the knowledge boundary of each character, resulting in degraded personalization and proneness to character hallucination in general domain. To address these problems, we draw inspirations from the context effect theory and propose a retrieval-based framework TAILORRPA to harvest tailored general domain instructions to improve integration of fine-grained memories and incorporate generaldomain protective queries to help shape the character-wise knowledge boundary, alleviating character hallucination. Based on the framework, we developed a role-playing dataset TAI-LORGEN, comprising both role-specific and general-domain instructions. Through empirical experiments, we proved the superiority of TAILORRPA in eliciting general domain roleplaying capabilities and alleviating character hallucination compared to baseline methods, and explored the existence of character hallucination in state-of-the-art proprietary models through empirical experiments, underlining the importance of our work.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MemoryBank: Enhancing Large Language Models with Long-Term Memory cites LoRA: Low-Rank Adaptation of Large Language Models
  • Character-LLM: A Trainable Agent for Role-Playing cites Generative Agents: Interactive Simulacra of Human Behavior
  • RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models cites LoRA: Low-Rank Adaptation of Large Language Models
  • RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models cites Generative Agents: Interactive Simulacra of Human Behavior
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on16

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  3. MemoryBank: Enhancing Large Language Models with Long-Term MemoryWanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye et al.AAAI 2024 · 394 citations
  4. RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language ModelsNoah Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu et al.ACL Findings 2024 · 120 citations
  5. Character-LLM: A Trainable Agent for Role-PlayingYunfan Shao, Linyang Li, Junqi Dai, Xipeng QiuEMNLP 2023 · 97 citations

Related papers

  1. CharacterCraft: Bridging the Literature-Reality Dialogue Gap for Practical Role-Playing AgentsXuyan Yin, Xinran Yang, Zihao Li, Lixin Zou et al.EMNLP Findings 2025
  2. ThinkPersona: Thinking with Persona Graphs for Faithful Individualized Role-PlayingYichen Cai, Pei Chen, Jiayang Li, Jingya Guo et al.ACL 2026
  3. Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMsKai Wang, Haoyang You, Yang Zhang, Zhongjie WangACL Findings 2026
  4. Mitigating Hallucination in Fictional Character Role-PlayNafis Sadeq, Zhouhang Xie, Byungkyu Kang, Prarit Lamba et al.EMNLP Findings 2024 · 6 citations
  5. CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based RewardsCheng Liu, Yifei Lu, Fanghua Ye, Jian Li et al.EMNLP 2025
Dusk over the sea between two cliffs drawn in fine vertical lines