cs.AINov 15, 2026

GEM-MM: Reducing VLM Hallucination with Entropy-Guided Preference Alignment

Authors: Yuanshan Chua, Xuejiao Zhao

Organizations: College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore · College of Computer Science, Sichuan University, China

Abstract

Vision-language models (VLMs) are routinely aligned with offline pairwise RLHF objectives, but multimodal preference data is scarce and treats every response token as equally informative. Under a small preference budget, pair construction becomes nearly irrelevant: standard DPO-style, image-conditional, and self-improvement objectives all perform within 1.1 points on MM-RLHF metrics and 0.5 points on hallucination rates, matching the SFT baseline. We call this entropy-blind preference optimization: the learning signal ignores policy uncertainty, which in chain-of-thought VLMs concentrates on specific fork tokens where visual claims are made. We introduce GEM-MM, extending entropy-guided preference modeling to VLMs. It samples on-policy candidates, rewards high-entropy reasoning forks, penalizes uncertain final answers, and updates the model via group-normalized policy gradients. On a 3000-prompt MM-RLHF budget with Qwen3-VL-4B-Instruct, GEM-MM achieves the best entropy-depth preference score (61.7% vs. 57.3-58.4% baselines) and implicit-reward accuracy (41.4%). Crucially, it reduces AMBER hallucination from 23.4-24.0 to 20.6 and CHAIR from 5.0-5.1 to 4.6 at matched caption coverage. It also ranks best on all three HallusionBench granularities, with a conservative operating point raising the near-chosen rate to 62.4%. An off-the-shelf multimodal reward model ranks GEM-MM first, and two such models independently confirm our main ablations (p < 0.001). We report confidence intervals, paired significance tests, metric-reward functional overlaps, and document a collapse mode when exceeding the fair budget. Code and evaluation harness: https://github.com/SNOWTEAM2023/GEM-MM

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

May 13, 2026

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling. We propose a stage-wise preference optimization framework for hallucination reduction through targeted multimodal data construction. Rather than directly optimizing on generic instruction-following data, our approach progressively constructs hallucination-focused preference pairs near known failure boundaries. The framework emphasizes ambiguous spatial orientation, object relationships, OCR uncertainty, and adversarial false-premise training. Hallucinated negatives are generated through minimally perturbed yet visually inconsistent alternatives, enabling Direct Preference Optimization (DPO) to better separate grounded reasoning from plausible hallucination. Experiments on open-source benchmarks and real-world multimodal evaluation scenarios demonstrate improved grounding consistency, reduced hallucination, and more informative grounded responses. Cross-model qualitative evaluation further shows that the proposed multimodal LLM DPO framework produces more visually grounded responses than several frontier proprietary VLMs, such as in ambiguous spatial reasoning and adversarial false-premise settings. The results suggest that hallucination may arise not only from limited model capacity, but also from inherent tendencies of autoregressive probabilistic generation to favor linguistically plausible continuations under weak visual grounding. Future work may explore physical consistency modeling, uncertainty-aware multimodal reasoning, and architectural alternatives beyond standard autoregressive decoding.
Jun 24, 2026

Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs

Vision-Language Models (VLMs) have shown strong performance in visual understanding, yet they still suffer from hallucinations, generating content that is not grounded in the image. Preference alignment is a promising approach to improve visual faithfulness, but its success depends heavily on how preference pairs are constructed. Existing methods exhibit two key limitations; (a) intervention-based methods often introduce significant deviation from the policy distribution, and (b) sampling-based methods often underuse visual information during the construction. In this paper, we propose ViPSy (Vision-driven Preference Synthesis), a framework for constructing preference data that are both policy-aligned and visually grounded. Our framework consists of two stages; in the first stage, ViPSy derives a visual cue from recurring object-level content across semantically aligned image variants, so preference construction can rely on visual information rather than language priors. In the second stage, ViPSy conditions the policy's own rollouts on this cue, allowing candidates to be guided by visually grounded content while staying close to the policy's response distribution. The resulting candidates remain close to the policy's response distribution while better leveraging visual information from the image. Experiments show that the resulting VLM, preference-aligned with ViPSy-constructed preference pairs, achieves a new state-of-the-art in hallucination mitigation. Compared with the previous state-of-the-art method, it reduces hallucination rates on AMBER and Object HalBench by 35.7% and 24.5%, respectively. The resulting model further improves on general visual grounding benchmarks, e.g., MMStar, MMVP, and CV-Bench, while also yielding gains in semantic segmentation and ImageNet linear probing, underscoring the effectiveness of our framework in enhancing the model's visual capabilities.
Jun 29, 2026

Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

Multimodal Large Language Models (MLLMs) are prone to hallucination as their generation preferences are insufficiently calibrated to visual evidence, causing them to fall back on linguistic priors, rather than faithful grounding. In this work, we start from an empirical observation: when query-relevant visual evidence is explicitly strengthened using the model's own attention, generation becomes more accurate, suggesting that many failures do not arise solely from missing perception, but from an insufficient tendency to trust the evidence the model has already attended to. Motivated by this finding, we propose Oriented Pickup Preference Optimization (OPPO), an evidence-aware alignment objective that learns preferences over the strength of visual evidence, rather than only response quality. Concretely, OPPO contrasts the same faithful response under stronger, anchored, weaker-evidence views, turning naive visual preference into ordered visual-evidence alignment. We further combine this objective with fine-grained span-level and token-level regularization to stabilize the training. Besides, we provide a theoretical analysis showing that ordered evidence margins induce a positive lower bound on local visual sensitivity. Extensive evaluations across hallucination and general-purpose benchmarks demonstrate that OPPO consistently outperforms baseline methods.