Papers with role-playing
PsyMem: Fine-grained Psychological Alignment and Explicit Memory Control for Advanced Role-Playing LLMs (2026.tacl-1)
Copied to clipboard
| Challenge: | Existing role-playing models rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimensions. |
| Approach: | They propose a framework that integrates fine-grained psychological attributes and explicit memory control for role-playing. |
| Outcome: | The proposed framework outperforms baseline models in human-likeness and character fidelity. |
Audio-Aware Large Language Models as Judges for Speaking Styles (2025.findings-emnlp)
Copied to clipboard
Cheng-Han Chiang, Xiaofei Wang, Chung-Ching Lin, Kevin Lin, Linjie Li, Radu Kopetz, Yao Qian, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang
| Challenge: | Audio-aware large language models (ALLMs) can understand textual and non-textual information in the audio input. |
| Approach: | They use audio-aware large language models (ALLMs) to evaluate the speaking styles of SLMs on two tasks: voice style instruction following and role-playing. |
| Outcome: | The proposed models can understand the textual and non-textual information in the audio input and can be used as a judge to assess the speaking styles of SLMs. |
Dealing with Controversy: An Emotion and Coping Strategy Corpus Based on Role Playing (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Psychological studies aim at explaining internal mechanisms of emotions, while computational studies simplify them into labels. |
| Approach: | They propose to treat emotions as strategies to cope with salient situations . they introduce a task of coping identification and a corpus constructed via role-playing . |
| Outcome: | The proposed method allows to investigate the link between emotions and behavior, which also emerges in language. |
Cultural Learning-Based Culture Adaptation of Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches for adapting large language models to diverse cultural values often rely on prompt engineering. |
| Approach: | They propose a framework for enhancing LLM alignment with cultural values based on cultural learning that leverages simulated social interactions to generate role-playing scenarios. |
| Outcome: | The proposed framework improves cultural value alignment across various model architectures measured using World Value Survey data. |
Aligning Large Language Models with Human Opinions through Persona Selection and Value–Belief–Norm Reasoning (2025.coling-main)
Copied to clipboard
| Challenge: | Current methods for reasoning and predicting human opinions employ role-playing with personae but face two major issues: LLMs are sensitive to even a single irrelevant persona, skewing predictions by up to 30%; and LLM fail to reason strategically over personas. |
| Approach: | They propose a four-step solution modeling which and how to reason with personae, inspired by the Value–Belief–Norm theory. |
| Outcome: | The proposed model improves existing methods by up to 4% by fine-tuning them with COO's data. |
SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration (2025.coling-main)
Copied to clipboard
Xin Guan, Nate Demchak, Saloni Gupta, Ze Wang, Ediz Ertekin Jr., Adriano Koshiyama, Emre Kazim, Zekun Wu
| Challenge: | Existing benchmarks for large language models fail to detect bias due to limited scope, contamination, and lack of a fairness baseline. |
| Approach: | They propose a benchmarking pipeline to detect biases in large language models . they use metrics for max disparity, impact ratio, and bias concentration to analyze disparity . |
| Outcome: | SAGED(bias) is the first holistic benchmarking pipeline to address biases in large language models. |
PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors (2026.findings-eacl)
Copied to clipboard
Donya Rooein, Sankalan Pal Chowdhury, Mariia Eremeeva, Yuan Qin, Debora Nozza, Mrinmaya Sachan, Dirk Hovy
| Challenge: | pedagogical theories are not aligned with teaching strategies for educational tasks . quiet students may be disengaged or not thinking critically because they do not speak up . |
| Approach: | They propose a taxonomy that links pedagogical methods to personality profiles to map teaching strategies to student personality traits. |
| Outcome: | The proposed model improves the use of less common, high-impact strategies such as role-playing . the model also increases the use less common strategies such role-players . |
Better Zero-Shot Reasoning with Role-Play Prompting (2024.naacl-long)
Copied to clipboard
Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, Xiaohang Dong
| Challenge: | Recent years have witnessed a paradigm shift in natural language processing, driven by large language models such as GPT-3, PaLM, and Llama. |
| Approach: | They propose a strategy for role-play prompting and assess its performance under the zero-shot setting. |
| Outcome: | The proposed method outperforms the standard zero-shot prompting approach across 12 reasoning benchmarks. |
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)
Copied to clipboard
Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo
| Challenge: | Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined. |
| Approach: | They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles . |
| Outcome: | The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles . |
Speaker Verification in Agent-generated Conversations (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have increased the capabilities of conversational AI to solve challenging dialogue problems. |
| Approach: | They propose a task to verify whether two sets of utterances originate from the same speaker. |
| Outcome: | The proposed task aims to verify whether two sets of utterances originate from the same speaker. |
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds (2025.naacl-long)
Copied to clipboard
| Challenge: | Evaluating role-playing capabilities in large language models is challenging due to complex dynamics involved in role-playering. |
| Approach: | They propose a simulation sandbox that generates situational fine-grained character behavior trajectories to enhance LLM performance. |
| Outcome: | The proposed model generates situational fine-grained character behavior trajectories to enhance performance. |
P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on personalized large language models focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making. |
| Approach: | They propose a personalized large language model (LLM) that captures implicit Big Five personality traits and integrates a Personality Specialization Loss to capture individual trait expressions. |
| Outcome: | The proposed model improves on Big Five personality traits and integrates a Personality Specialization Loss (PSL) to capture individual trait expressions. |
TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage (2024.findings-emnlp)
Copied to clipboard
| Challenge: | escalation in emergency department patient visits poses challenges to efficient clinical management . Currently, hospitals rely on human experts to review clinical notes and determine case urgency . |
| Approach: | a team of researchers develop a multi-agent framework to enhance collaborative decision-making in clinical triage. |
| Outcome: | The proposed framework outperforms state-of-the-art LLM-based methods on three clinical triage test sets. |
PersonaForge: Psychology-Grounded Dual-Process Architecture for Personality-Consistent Role-Playing Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to role-playing with Large Language Models lack consistency across long conversations. |
| Approach: | They propose a three-layer personality architecture grounded in psychological theory and a dual-process generation mechanism inspired by cognitive science to solve this problem. |
| Outcome: | The proposed framework reduces drift over 50-turn conversations by reducing personality consistency . human evaluation confirms more authentic and psychologically coherent character behaviors. |
UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)
Copied to clipboard
Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, Mengting Hu
| Challenge: | Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs . |
| Approach: | They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities. |
| Outcome: | The proposed method outperforms existing methods for benchmarking the uncertainty of large language models. |
Reasoning Does Not Necessarily Improve Role-Playing Ability (2025.findings-acl)
Copied to clipboard
| Challenge: | a study compares zero-shot role-playing, reasoning-optimized LLMs, and reasoning-based LLM. |
| Approach: | They propose to use reasoning-optimized LLMs to improve role-playing performance . they propose to develop a chain-of-thought-based learning system that can be used to improve LLM performance if reasoning is used . |
| Outcome: | The proposed research compares zero-shot role-playing, role-playering with Chain-of-Thought, and reasoning-optimized LLMs. |
Beyond Dialogue: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model (2025.acl-long)
Copied to clipboard
| Challenge: | Existing role-playing training methods often lack profile-dialogue alignment at the sentence level. |
| Approach: | They propose a framework that aligns dialogue with profile traits for each scenario, eliminating biases during training. |
| Outcome: | The proposed model outperforms most proprietary role-playing models and is fully automated and low-cost. |
Can LLM be a Personalized Judge? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a new study examines the reliability of large language models (LLMs) for personalization and role-playing evaluation without examining its validity. |
| Approach: | They investigate the reliability of LLM-as-a-Personalized-Judge for personalization . they find that personas provided to LLMs have limited predictive power . |
| Outcome: | The proposed model is less reliable than previously thought, the authors show . human annotation reveals that third-person crowd worker evaluations of personalized preferences are even worse than LLM predictions. |
LEGO: A Multi-agent Collaborative Framework with Role-playing and Iterative Feedback for Causality Explanation Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Causality explanation generation is a generative task that aims to explain why a given cause-effect pair is true using natural language. |
| Approach: | They propose a multi-agent framework with role-playing and iterative feedback for causality explanation generation. |
| Outcome: | The proposed framework is superior to existing frameworks on WIKIWHY and e-CARE datasets. |
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)
Copied to clipboard
Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Yongbin Li
| Challenge: | Existing approaches to reward modeling in reinforcement learning tasks are limited when dealing with ambiguous preferences. |
| Approach: | They propose to use AAM to dynamically calibrate preference margins using the Bradley-Terry model's internal parameter knowledge to improve reward modeling in subjective tasks. |
| Outcome: | The proposed approach improves reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge. |
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2024.findings-acl)
Copied to clipboard
Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, Junran Peng
| Challenge: | Large Language Models (LLMs) have paved the way for complex tasks such as role-playing. |
| Approach: | They propose a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models. |
| Outcome: | The proposed framework improves role-playing abilities with 168,093 samples. |
On Guardrail Models’ Robustness to Mutations and Adversarial Attacks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | generative AI systems providing unsafe information has raised significant concerns, emphasizing the need for safety guardrails. |
| Approach: | They propose to evaluate 15 state-of-the-art guardrail models to assess their robustness to input mutations and adversarial attacks designed to bypass models’ safety alignment. |
| Outcome: | The proposed models are robust to input mutations and adversarial attacks that bypass models’ safety alignment. |
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have impressive capabilities across various domains, including role-playing, creative writing, mathematical reasoning, and coding. |
| Approach: | They propose two methods to improve the model’s adherence to length constraints and copy-paste accuracy without compromising response quality. |
| Outcome: | The proposed methods improve the model’s adherence to length constraints and copy-paste accuracy without compromising response quality. |
CoE: A Clue of Emotion Framework for Emotion Recognition in Conversations (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are limited in interpreting complex conversational streams. |
| Approach: | They propose a Clue of Emotion framework which integrates key conversational clues to enhance the ERC task. |
| Outcome: | The proposed framework outperforms EmoryNLP, MELD, and IEMOCAP in the role-playing, speaker identification, and emotion reasoning tasks. |
Enhancing Persona Consistency for LLMs’ Role-Playing using Persona-Aware Contrastive Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for analyzing and analyzing large language models (LLMs) lack of emotion and fine-grained role awareness limits the model’s ability to provide personalized and diverse interactions further. |
| Approach: | They propose an annotation-free framework to align LLMs’ behavior during role-playing, enhancing the model’s role consistency. |
| Outcome: | The proposed framework outperforms vanilla LLMs under automatic evaluation methods and human expert evaluation. |
R-CHAR: A Metacognition-Driven Framework for Role-Playing in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing role-playing structures lack cognitive consistency in complex scenarios . Existing models excel in math and coding tasks but lack coherent reasoning . |
| Approach: | They propose a metacognition-driven framework that enhances role-playing performance . experimental results show performance improvements across varying scenario complexities . |
| Outcome: | The proposed framework outperforms existing models in social intelligence tasks and shows strength in long-context comprehension and group-level social interactions. |
Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on large language models (LLMs) fail to detect character knowledge errors, leading to low-quality automatic corpus construction. |
| Approach: | They propose to use a large language model to detect known knowledge errors and an agent-based reasoning method to improve error detection. |
| Outcome: | The proposed method improves the ability of LLMs to detect errors in known knowledge errors and unknown knowledge errors while playing roles. |
ChatAnime: Towards User-Centered Emotional Support in LLM-based Virtual Character Chat (2026.acl-long)
Copied to clipboard
| Challenge: | Existing research focuses on character consistency in fictional or game-based scenarios . ESRP framework is designed to align role-playing with real-world user scenarios based on emotional needs. |
| Approach: | They propose a framework to align role-playing with real-world user scenarios and emotional needs. |
| Outcome: | The proposed framework aligns role-playing with real-world user scenarios and emotional needs. |