LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Weiyue, Song, Mingxiao, Shen, Zhenda, Zhao, Dachuan, Long, Yunfan, Li, Yi, Li, Yongce, Yang, Ruyi, Wang, Mengyu
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915725650690048
author Li, Weiyue
Song, Mingxiao
Shen, Zhenda
Zhao, Dachuan
Long, Yunfan
Li, Yi
Li, Yongce
Yang, Ruyi
Wang, Mengyu
author_facet Li, Weiyue
Song, Mingxiao
Shen, Zhenda
Zhao, Dachuan
Long, Yunfan
Li, Yi
Li, Yongce
Yang, Ruyi
Wang, Mengyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08003
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback
Li, Weiyue
Song, Mingxiao
Shen, Zhenda
Zhao, Dachuan
Long, Yunfan
Li, Yi
Li, Yongce
Yang, Ruyi
Wang, Mengyu
Computation and Language
Artificial Intelligence
Multiagent Systems
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.
title LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback
topic Computation and Language
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2601.08003