CLAIAug 8, 2025

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation

arXiv:2508.06046v11 citationsh-index: 8Has Code
Originality Highly original
AI Analysis

This addresses the challenge of evaluating open-ended story generation tasks, which is crucial for both human judgment and guiding AI story generation systems.

The paper tackles the problem of accurate story evaluation for LLMs by proposing EvolvR, a self-evolving pairwise reasoning framework that achieves state-of-the-art performance on three benchmarks and significantly enhances generated story quality when used as a reward model.

Although the effectiveness of Large Language Models (LLMs) as judges (LLM-as-a-judge) has been validated, their performance remains limited in open-ended tasks, particularly in story evaluation. Accurate story evaluation is crucial not only for assisting human quality judgment but also for providing key signals to guide story generation. However, existing methods face a dilemma: prompt engineering for closed-source models suffers from poor adaptability, while fine-tuning approaches for open-source models lack the rigorous reasoning capabilities essential for story evaluation. To address this, we propose the Self-Evolving Pairwise Reasoning (EvolvR) framework. Grounded in pairwise comparison, the framework first self-synthesizes score-aligned Chain-of-Thought (CoT) data via a multi-persona strategy. To ensure data quality, these raw CoTs undergo a self-filtering process, utilizing multi-agents to guarantee their logical rigor and robustness. Finally, the evaluator trained on the refined data is deployed as a reward model to guide the story generation task. Experimental results demonstrate that our framework achieves state-of-the-art (SOTA) performance on three evaluation benchmarks including StoryER, HANNA and OpenMEVA. Furthermore, when served as a reward model, it significantly enhances the quality of generated stories, thereby fully validating the superiority of our self-evolving approach.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes