Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization

• URL: http://arxiv.org/abs/2509.25717v1
• Date: Tue, 30 Sep 2025 03:24:09 GMT
• Title: Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization
• Authors: Xintong Li, Chuhan Wang, Junda Wu, Rohan Surana, Tong Yu, Julian McAuley, Jingbo Shang,
• Abstract summary: We propose MISP-DPO, the first framework to incorporate multiple, semantically diverse negative images in multimodal DPO.<n>Our method embeds prompts and candidate images in CLIP space and applies a sparse autoencoder to uncover semantic deviations into interpretable factors.<n>Experiments across five benchmarks demonstrate that MISP-DPO consistently improves multimodal alignment over prior methods.
• Score: 68.64764778089229
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Direct Preference Optimization (DPO) has recently been extended from text-only models to vision-language models. However, existing methods rely on oversimplified pairwise comparisons, generating a single negative image via basic perturbations or similarity-based retrieval, which fail to capture the complex nature of multimodal preferences, inducing optimization bias and hallucinations. To address this issue, we propose MISP-DPO, the first framework to incorporate multiple, semantically diverse negative images in multimodal DPO via the Plackett-Luce model. Our method embeds prompts and candidate images in CLIP (Contrastive Language-Image Pretraining) space and applies a sparse autoencoder to uncover semantic deviations into interpretable factors. Negative samples are selected based on reconstruction difficulty, semantic deviation from the positive, and mutual diversity, yielding broader and more informative supervision. To handle multi-negative comparisons, we adopt a Plackett-Luce objective and introduce an importance sampling strategy that improves training efficiency. Experiments across five diverse benchmarks demonstrate that MISP-DPO consistently improves multimodal alignment over prior methods, validating the effectiveness of semantic-aware, multi-negative sampling in preference-based learning.

Related papers

• Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation [60.33386541343322]
  We propose a Multimodal Large Language Models framework that integrates Hardness-aware and Noise-regularized preference optimization for Recommendation (HaNoRec)<n>Specifically, HaNoRec dynamically adjusts optimization weights based on both the estimated hardness of each training sample and the policy model's real-time responsiveness.
  arXiv  Detail & Related papers  (2025-11-24T04:10:46Z)
• Beyond Single-Reward: Multi-Pair, Multi-Perspective Preference Optimization for Machine Translation [44.04325848740683]
  We introduce M2PO: Multi-Pair, Multi-Perspective Preference Optimization.<n>Our framework integrates a multi-perspective reward engine that creates a more robust signal.<n>On challenging WMT21-22 benchmarks, M2PO substantially outperforms existing preference optimization methods.
  arXiv  Detail & Related papers  (2025-10-15T11:30:49Z)
• Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs [74.74767980885758]
  We propose Context-to-Cue Direct Preference Optimization (CcDPO), a multi-level preference optimization framework.<n>CcDPO enhances per-image perception in multi-image settings by zooming into visual clues -- from sequential context to local details.<n> Experiments show that CcDPO significantly reduces hallucinations and yields consistent performance gains.
  arXiv  Detail & Related papers  (2025-05-28T14:24:02Z)
• Preference Optimization with Multi-Sample Comparisons [53.02717574375549]
  We introduce a novel approach that extends post-training to include multi-sample comparisons.<n>These approaches fail to capture critical characteristics such as generative diversity and bias.<n>We demonstrate that multi-sample comparison is more effective in optimizing collective characteristics than single-sample comparison.
  arXiv  Detail & Related papers  (2024-10-16T00:59:19Z)
• mDPO: Conditional Preference Optimization for Multimodal Large Language Models [52.607764280030196]
  Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement. We propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference.
  arXiv  Detail & Related papers  (2024-06-17T17:59:58Z)
• Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
  We introduce a novel closed-form formulation for direct preference optimization using multiple reference models. The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models. Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
  arXiv  Detail & Related papers  (2024-05-26T00:29:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.