Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
read the original abstract
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
This paper has not been read by Pith yet.
Forward citations
Cited by 12 Pith papers
-
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
-
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Psy-CoT decomposes reasoning into Interaction Perception, Psychological Empathy, and Logical Construction while RAPO asymmetrically weights role-specific tokens during policy optimization, outperforming prior CoT and ...
-
Dynamic In-Group Persona Generation for Enhancing Human-AI Rapport
Dynamic in-group persona generation for LLMs, conditioned on user concern, significantly improves perceived rapport and user experience over no-persona and minimal-disclosure baselines in a human-subject study.
-
Towards Automated Crowdsourced Testing via Personified-LLM
PersonaTester uses LLMs guided by three-dimensional personas to replicate crowdworker testing patterns, yielding higher behavioral consistency, variability, and more bug detections than baseline LLM agents.
-
HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling
HyMem introduces dual-granular memory storage with a lightweight summary module for fast responses and selective activation of a deep LLM module for complex queries, outperforming full-context baselines by 92.6% lower...
-
How Humans Help LLMs: Assessing and Incentivizing Human Preference Annotators
Develops self-consistency monitoring for preference annotators and derives sample-complexity bounds showing linear contracts achieve near-ideal performance faster than binary ones under continuous actions.
-
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents
AdaPlan-H enables LLM agents to generate self-adaptive hierarchical plans that adjust detail level to task difficulty, improving success rates in multi-step tasks.
-
From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes
Demographic-only LLM agents for retirement survey prediction exhibit central tendency bias, fail to reproduce incorrect or 'don't know' answers, and miss factor interactions in regressions, unlike survey-anchored agents.
-
Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents
A 3x3 between-subjects experiment finds that risk-contingent autonomy in LLM agents attenuates personalization's negative effects on privacy concerns and trust via increased perceived control.
-
Fairness Testing of Large Language Models in Role-Playing
Generates 550 roles and 33,000 questions to evaluate 10 LLMs in role-playing, finding 107,580 biased responses.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.