# Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment

Source: [Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment](<https://www.sota2.com/research/paper/68fa7a381e209131cea81e34>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:15:13.470Z

Authors: Ying Ba, Tianyu Zhang, Yalong Bai, Wenyi Mo, Tao Liang, Bing Su, Ji-Rong Wen

Published: 2025-07-25T07:01:50.000Z

## Abstract

Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human preference reward models fine-tuned based on CLIP and BLIP architectures have inherent flaws: they inappropriately assign low scores to images with rich details and high aesthetic value, creating a significant discrepancy with actual human aesthetic preferences. To address this issue, we design a novel evaluation score, ICT (Image-Contained-Text) score, that achieves and surpasses the objectives of text-image alignment by assessing the degree to which images represent textual content. Building upon this foundation, we further train an HP (High-Preference) score model using solely the image modality to enhance image aesthetics and detail quality while maintaining text-image alignment. Experiments demonstrate that the proposed evaluation model improves scoring accuracy by over 10\\% compared to existing methods, and achieves significant results in optimizing state-of-the-art text-to-image models. This research provides theoretical and empirical support for evolving image generation technology toward higher-order human aesthetic preferences. Code is available at https://github.com/BarretBa/ICTHP.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-Reward Alignment on Parti-Prompts](<https://www.sota2.com/research/sota/multi-reward-alignment-on-parti-prompts.md>): Multi-Reward Alignment; Parti-Prompts; CLIP Score: 0.3548.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.19002>)

[PDF](<https://arxiv.org/pdf/2507.19002.pdf>)