Pith. sign in

REVIEW 11 cited by

mDPO: Conditional Preference Optimization for Multimodal Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.11839 v2 pith:UPQ23KJT submitted 2024-06-17 cs.CV cs.AIcs.CLcs.LG

Fei Wang , Wenxuan Zhou , James Y. Huang , Nan Xu , Sheng Zhang , Hoifung Poon , Muhao Chen This is my paper
classification cs.CVcs.AIcs.CLcs.LG
keywords preferencemultimodaloptimizationproblemmdpomodelimagelanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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. Through a comparative experiment, we identify the unconditional preference problem in multimodal preference optimization, where the model overlooks the image condition. To address this problem, we propose mDPO, a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference. Moreover, we introduce a reward anchor that forces the reward to be positive for chosen responses, thereby avoiding the decrease in their likelihood -- an intrinsic problem of relative preference optimization. Experiments on two multimodal LLMs of different sizes and three widely used benchmarks demonstrate that mDPO effectively addresses the unconditional preference problem in multimodal preference optimization and significantly improves model performance, particularly in reducing hallucination.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MentalThink: Shaping Thoughts in Mental SVG World

    cs.AI 2026-07 conditional novelty 7.0 of 10

    MLLMs that generate and render SVG sketches as multi-turn intermediate reasoning steps reach 55.1% on VSIBench and 76.0% on MindCube, far above the Qwen2.5-VL-7B backbone.

  2. LPOI: Listwise Preference Optimization for Vision Language Models

    cs.CV 2025-05 conditional novelty 7.0 of 10

    LPOI reduces VLM hallucination by training the model to prefer the original image over progressively masked versions of the same image, using a listwise ranking loss built from pairwise preference data.

  3. Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Groc-PO applies preference optimization at three grounded stages — object grounding, contextual grounding, grounded reasoning — and outperforms final-answer-only DPO on hallucination and complex-reasoning benchmarks.

  4. Adaptive Perturbation Selection for Contrastive Audio Decoding

    cs.SD 2026-06 unverdicted novelty 6.0 of 10

    A learned per-example router over a 105-perturbation audio library improves contrastive decoding for audio-LLM hallucination, with task-dependent best distortions (e.g., reverse audio for temporal order).

  5. Controlling Multimodal LLMs via Reward-guided Decoding

    cs.CV 2025-08 conditional novelty 6.0 of 10

    MRGD guides MLLM decoding with a learned hallucination reward and a detector-based recall reward, allowing users to trade off object precision, recall, and test-time compute while reducing object hallucinations on CHA...

  6. Explicit Preference Optimization: No Need for an Implicit Reward Model

    cs.LG 2025-06 conditional novelty 6.0 of 10

    EXPO is a pair of explicit preference-optimization losses that provably avoid DPO's uniform-regularization and poor-interpolation failure modes and outperform DPO on Anthropic HH and IMDb.

  7. ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A reinforcement-learned frame selection policy, trained with reward margins from a reference video-LLM, improves video QA accuracy of LLaVA-OV and InternVL3 across several benchmarks.

  8. MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Multi-domain RLVR data mixing, guided by a quadratic surrogate fitted to 11 pilot runs, improves a Qwen2-VL-2B model's out-of-distribution accuracy by about 5 points over uniform mixing.

  9. MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models

    cs.CV 2025-07 conditional novelty 4.0 of 10

    MCA-LLaVA reindexes image tokens by sums of mirrored 2D coordinates so instruction tokens attend across the whole image, reducing hallucination on POPE, CHAIR, and MME.

  10. DPO Learning with LLMs-Judge Signal for Computer Use Agents

    cs.AI 2025-06 conditional novelty 4.0 of 10

    An LLM-as-Judge pipeline that scores synthetic GUI interaction trajectories and fine-tunes a 2B model with DPO yields a local computer-use agent that beats its base model on 15-step OSWorld tasks.

  11. ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning

    cs.CL 2025-05 reject novelty 2.0 of 10

    ASPO's adaptive sentence-level loss, by the paper's own definitions, reduces exactly to the standard DPO loss, leaving no difference in the optimization objective.

Pith tools