LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback

TL;DR

This paper introduces LLM Review, a peer-review-inspired framework for enhancing creative writing with large language models, demonstrating improved performance and diversity through targeted feedback and a novel evaluation dataset.

Contribution

The paper proposes a novel Blind Peer Review framework for LLMs that preserves creativity and introduces SciFi-100, a new dataset for evaluating science fiction writing quality.

Findings

LLM Review outperforms multi-agent baselines.

Smaller models with our framework can surpass larger models.

Interaction structure can substitute for model scale.

Abstract

Large Language Models (LLMs) often struggle with creative generation, and multi-agent frameworks that improve reasoning through interaction can paradoxically hinder creativity by inducing content homogenization. We introduce LLM Review, a peer-review-inspired framework implementing Blind Peer Review: agents exchange targeted feedback while revising independently, preserving divergent creative trajectories. To enable rigorous evaluation, we propose SciFi-100, a science fiction writing dataset with a unified framework combining LLM-as-a-judge scoring, human annotation, and rule-based novelty metrics. Experiments demonstrate that LLM Review consistently outperforms multi-agent baselines, and smaller models with our framework can surpass larger single-agent models, suggesting interaction structure may substitute for model scale.