Learning to Rank Caption Chains for Video-Text Alignment

Read full text Summarise with VIRAT
Authors: Ansel Blume, Burak Uzkent, Shalini Chaudhuri, Garin N. Kessler
Cited by: 0
References: 40

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Direct preference optimization (DPO) is an effective technique to train language models to generate preferred over dispreferred responses. However, this binary "winner-takes-all" approach is suboptimal for vision-language models whose response quality is highly dependent on visual content. In particular, a response may still be faithful to the visual inputs even if it is less preferable than an alternative. The standard Bradley-Terry DPO formulation lacks this nuance, upweighting winning responses without sufficient regard for whether the "losing" response still maintains high visual fidelity. In this work, we investigate ranking optimization as an alternative that more precisely situates responses' faithfulness to visual inputs. We focus on video-text alignment using detailed video captions, proposing a method to generate challenging, totally ordered caption chains at scale through repeated caption degradation. Our results show ranking optimization outperforms binary DPO for long-form content generation and assessment, and importantly, we find that these approaches require finetuning of the vision encoder to be effective, challenging the view of DPO as purely a language-reweighting process.

Fields of Study & Subjects

Multimodal Machine Learning Applications Generative Adversarial Networks and Image Synthesis Topic Modeling

Publication details

Journal / source
arXiv (Cornell University)
Publication date
26 March 2026
Language
EN
Document type
Preprint