PREFINE: Personalized Story Generation via Simulated User Critics and User-Specific Rubric Generation

TL;DR

PREFINE introduces a novel critique-and-refine framework for personalized story generation that constructs user-specific rubrics and pseudo-user agents, achieving better personalization without requiring user feedback or model fine-tuning.

Contribution

The paper presents PREFINE, a new inference-only method that personalizes stories through simulated critiques and user-specific rubrics, avoiding explicit feedback and parameter updates.

Findings

PREFINE outperforms existing personalization methods on benchmark datasets.

User-specific rubrics are key to effective personalization.

The approach enhances already personalized outputs through post-hoc refinement.

Abstract

Personalizing story generation to individual users remains a core challenge in natural language generation. Existing approaches typically require explicit user feedback or fine-tuning, which pose practical concerns in terms of usability, scalability, and privacy. In this work, we introduce PREFINE (Persona-and-Rubric Guided Critique-and-Refine), a novel Critique-and-Refine framework that enables personalized story generation without user feedback or parameter updates. PREFINE constructs a pseudo-user agent from a user's interaction history and generates user-specific rubrics (evaluation criteria). These components are used to critique and iteratively refine story drafts toward the user's preferences. We evaluate PREFINE on two benchmark datasets, PerDOC and PerMPST, and compare it with existing approaches. Both automatic and human evaluations show that PREFINE achieves significantly better personalization while preserving general story quality. Notably, PREFINE outperforms existing in-context personalization and critique-based generation methods, and can even enhance already personalized outputs through post-hoc refinement. Our analysis reveals that user-specific rubrics are critical in driving personalization. The results demonstrate the effectiveness and practicality of inference-only, rubric-guided personalization, with potential applications beyond storytelling, including dialogue, recommendation, and education.