# Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization

arXiv: https://arxiv.org/abs/2509.16560 · HTML: https://mlsanity.com/paper/2509.16560/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [UniIR: Training and Benchmarking Universal Multimodal Information Retrievers](https://mlsanity.com/paper/2311.17136/) (2023)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant](https://mlsanity.com/paper/2412.01720/) (2024)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?](https://mlsanity.com/paper/2301.00184/) (2022)
- [VindLU: A Recipe for Effective Video-and-Language Pretraining](https://mlsanity.com/paper/2212.05051/) (2022)
- [DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO](https://mlsanity.com/paper/2506.07464/) (2025)
- [Unified Coarse-to-Fine Alignment for Video-Text Retrieval](https://mlsanity.com/paper/2309.10091/) (2023)
- [CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs](https://mlsanity.com/paper/2408.10433/) (2024)
- [Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence](https://mlsanity.com/paper/2406.10957/) (2024)
- [LLaMo: Large Language Model-based Molecular Graph Assistant](https://mlsanity.com/paper/2411.00871/) (2024)
- [Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions](https://mlsanity.com/paper/2503.05186/) (2025)
- [VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning](https://mlsanity.com/paper/2501.06761/) (2025)
- [EA-VTR: Event-Aware Video-Text Retrieval](https://mlsanity.com/paper/2407.07478/) (2024)

## Built on by (most cited first, 1 of 1)

- [VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement](https://mlsanity.com/paper/2607.00446/) (2026)

## Abstract (arXiv)

In text-video retrieval, auxiliary captions are often used to enhance video understanding, bridging the gap between the modalities. While recent advances in multi-modal large language models (MLLMs) have enabled strong zero-shot caption generation, we observe that such captions tend to be generic and indistinguishable across visually similar videos, limiting their utility for fine-grained retrieval. Moreover, conventional captioning approaches are typically evaluated using language generation metrics, such as BLEU, which are not typically tailored for retrieval tasks that require making discriminative distinctions between candidates. To address this, we propose CaRe-DPO, a retrieval framework that directly optimizes caption generation using retrieval relevance scores. At its core is Dual-Group Direct Preference Optimization (DG-DPO), a novel learning strategy that supervises captioning by modeling preferences across groups of distinct video and caption pairs. In addition, we present an MLLM-based retrieval model that incorporates role-embeddings to better distinguish between textual inputs with different functional roles, such as an auxiliary caption and a text query. Through extensive experiments, we demonstrate that CaRe-DPO significantly enhances retrieval performance by effectively leveraging auxiliary knowledge to generate fine-grained captions for retrieval. Code is available at https://github.com/mlvlab/CaReDPO.