Persona-Pruner: Sculpting Lightweight Models for Role-Playing

• URL: http://arxiv.org/abs/2606.14695v1
• Date: Fri, 12 Jun 2026 17:58:08 GMT
• Title: Persona-Pruner: Sculpting Lightweight Models for Role-Playing
• Abstract summary: We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description.<n>Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art pruning techniques.
• Score: 23.98750330758078
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona. However, applying these capabilities to real-world applications (e.g., ecosystems with numerous NPCs interacting simultaneously) exposes a critical inefficiency due to the excessive computational cost. In this paper, we question the necessity of dedicating a full, generalist model to a single persona, hypothesizing that a specific character identity relies on only a fraction of the model's total capacity. We observe that naively pruning LMs often severely degrades the role-playing performance for a specific persona; it does not distinguish between redundant knowledge and essential character traits. We propose Persona-Pruner, a framework that sculpts a lightweight role-playing model by isolating persona-specific sub-networks from a single description. Our experiments consistently show that Persona-Pruner preserves role-playing performance substantially more effectively than existing state-of-the-art LLM pruning techniques, reducing the performance drop from the dense model by up to 93.8% over the strongest baseline on RoleBench in LLM-as-a-judge score, while still maintaining general LLM capabilities. Code is available at https://github.com/jsu-kim/Persona-Pruner.

Related papers

• Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization [62.82109000444373]
  Psy-CoT is a chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps.<n>Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods.
  arXiv  Detail & Related papers  (2026-06-25T13:34:47Z)
• TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation [55.55404595177229]
  Large Language Models (LLMs) are exhibiting emergent human-like abilities.<n>TwinVoice is a benchmark for assessing persona simulation across diverse real-world contexts.
  arXiv  Detail & Related papers  (2025-10-29T14:00:42Z)
• PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play? [13.537861623851054]
  We present PersonaEval, the first benchmark designed to test whether role evaluators can reliably identify human roles.<n>Our experiments, including a human study, show that even the best-performing LLMs reach only around 69% accuracy.<n>To better understand this gap, we examine training-time adaptation and test-time compute, suggesting that reliable evaluation requires more than task-specific tuning.
  arXiv  Detail & Related papers  (2025-08-06T13:06:15Z)
• RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing [133.0641538589466]
  RMTBench is a comprehensive textbfuser-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.<n>Our benchmark constructs dialogues based on explicit user motivations rather than character descriptions, ensuring alignment with practical user applications.<n>By shifting focus from character background to user intention fulfillment, RMTBench bridges the gap between academic evaluation and practical deployment requirements.
  arXiv  Detail & Related papers  (2025-07-27T16:49:47Z)
• Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language Agent [18.67432557362308]
  Test-Time-Matching (TTM) is a training-free role-playing framework through test-time scaling and context engineering.<n>Our framework involves a structured, three-stage generation pipeline that utilizes these features for controlled role-playing.<n>It achieves high-fidelity role-playing performance, also enables seamless combinations across diverse linguistic styles and even variations in personality and memory.
  arXiv  Detail & Related papers  (2025-07-22T17:47:44Z)
• Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning [7.836439251883518]
  We propose a novel framework named textbfunderlinePersona-Aware textbfunderlineContrastive textbfunderlineLearning (PCL) to align model role-playing behavior.<n>We show that PCL significantly outperform vanilla LLMs under automatic evaluation methods and human expert evaluation.
  arXiv  Detail & Related papers  (2025-03-22T06:12:34Z)
• OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas [65.83634577897564]
  This study explores a large-scale data synthesis approach to equip large language models with character generalization capabilities.<n>We begin by synthesizing large-scale character profiles using personas from Persona Hub.<n>We then explore two strategies: response rewriting and response generation, to create character-aligned instructional responses.
  arXiv  Detail & Related papers  (2025-01-26T07:07:01Z)
• CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds [74.02480671181685]
  Role-playing is a crucial capability of Large Language Models (LLMs)<n>Current evaluation methods fall short of adequately capturing the nuanced character traits and behaviors essential for authentic role-playing.<n>We propose CharacterBox, a simulation sandbox designed to generate situational fine-grained character behavior trajectories.
  arXiv  Detail & Related papers  (2024-12-07T12:09:35Z)
• Thinking Before Speaking: A Role-playing Model with Mindset [0.6428333375712125]
  Large Language Models (LLMs) are skilled at simulating human behaviors. These models tend to perform poorly when confronted with knowledge that the assumed role does not possess. We propose a Thinking Before Speaking (TBS) model in this paper.
  arXiv  Detail & Related papers  (2024-09-14T02:41:48Z)
• Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment [62.898963074989766]
  We introduce Ditto, a self-alignment method for role-play. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold. We present the first comprehensive cross-supervision alignment experiment in the role-play domain.
  arXiv  Detail & Related papers  (2024-01-23T03:56:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.