SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.04831 · 2026

StoryAlign: Evaluating and Training Reward Models for Story Generation

Hao Peng, Juanzi Li, Lei Hou, Xiaozhi Wang, Yunjia Qi, Haotian Xia

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored works regarding complex narrative structure and human-aligned preferences. A key reason is the absence of effective modeling of human story preferences, which are inherently subjective and under-explored. In this work, we systematically evaluate the modeling of human story preferences and introduce STORYRMB, the first benchmark for assessing reward models on story preferences. STORYRMB contains 1, 133 high-quality, human-verified instances, each consisting of a prompt, one chosen story, and three rejected stories. We find existing reward models struggle to select human-preferred stories, with the best model achieving only 66.3% accuracy. To address this limitation, we construct roughly 100, 000 high-quality story preference pairs across diverse domains and develop STORYREWARD, an advanced reward model for story preference trained on this dataset. STORYREWARD achieves state-of-the-art (SoTA) performance on STORYRMB, outperforming much larger models. We also adopt STORYREWARD in downstream test-time scaling applications for best-of-n (BoN) story selection and find that it generally chooses stories better aligned with human preferences. We will release our dataset, model, and code to facilitate future research. Related code and data are available at https://github.com/THU-KEG/StoryAlign.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.04831")
get_code_for_paper("2605.04831")
have("2605.04831")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2605.04831.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2605.04831.svg)](https://syntology.ai/paper/2605.04831)

Connect an agent — have() is free.