Pith. sign in

REVIEW 4 cited by

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.15427 v2 pith:5SSGVMSD submitted 2025-01-26 cs.CL

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas

classification cs.CL
keywords characterrole-playinggeneralizationlarge-scalellmsmodelsyntheticcustomizable
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Customizable role-playing in large language models (LLMs), also known as character generalization, is gaining increasing attention for its versatility and cost-efficiency in developing and deploying role-playing dialogue agents. This study explores a large-scale data synthesis approach to equip LLMs with character generalization capabilities. We begin by synthesizing large-scale character profiles using personas from Persona Hub and then explore two strategies: response rewriting and response generation, to create character-aligned instructional responses. To validate the effectiveness of our synthetic instruction tuning data for character generalization, we perform supervised fine-tuning (SFT) using the LLaMA-3 8B model. Our best-performing model strengthens the original LLaMA-3 8B Instruct model and achieves performance comparable to GPT-4o models on role-playing dialogue. We release our synthetic characters and instruction-tuning dialogues to support public research.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BOOKMARKS: Efficient Active Storyline Memory for Role-playing

    cs.CL 2026-05 unverdicted novelty 7.0

    BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.

  2. Efficient Safety Alignment of Language Models via Latent Personality Traits

    cs.LG 2026-07 conditional novelty 6.0

    Latent adversarial training on 66 harm-agnostic Big-Five personality statements yields near-zero HarmBench ASR across direct requests and five jailbreaks while preserving utility.

  3. Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

    cs.CL 2026-06 unverdicted novelty 6.0

    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 ...

  4. Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents

    cs.CL 2026-06 unverdicted novelty 6.0

    REVERIEMEM is a three-layer perspective-bounded memory system that raises knowledge boundary fidelity by 34.6 points and wins ~79% of narrative comparisons on a new book-based role-playing benchmark.