dorsal/arxiv
View SchemaLLM Review: Enhancing Creative Writing via Blind Peer Review Feedback
| Authors | Weiyue Li, Mingxiao Song, Zhenda Shen, Dachuan Zhao, Yunfan Long, Yi Li, Yongce Li, Ruyi Yang, Mengyu Wang |
|---|---|
| Categories | |
| ArXiv ID | 2601.08003vv1 |
| URL | https://arxiv.org/abs/2601.08003 |
| License | http://creativecommons.org/licenses/by/4.0/ |
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.
{
"annotation_id": "5f607dd8-56ee-4582-a7d3-7b36ca5e8018",
"date_created": "2026-02-17T05:53:15.042000Z",
"date_modified": "2026-02-17T05:53:15.042000Z",
"file_hash": "5ca49e653673e0e4bd6baa819058683dbf448346231b75c5421ec89cff9947a5",
"private": false,
"record": {
"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.",
"arxiv_id": "2601.08003",
"authors": [
"Weiyue Li",
"Mingxiao Song",
"Zhenda Shen",
"Dachuan Zhao",
"Yunfan Long",
"Yi Li",
"Yongce Li",
"Ruyi Yang",
"Mengyu Wang"
],
"categories": [
"cs.CL",
"cs.AI",
"cs.MA"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback",
"url": "https://arxiv.org/abs/2601.08003",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "84e89a3a-23e8-4871-b00d-f68d83695382",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}