This paper introduces {S-MME}, a benchmark designed to systematically diagnose shortcut-biased behavior in MLLMs, and proposes a training-free framework, Counterfactual Long-video Evidence-Aware Reasoning (CLEAR), which is generalizable and can be integrated in different MLLMs, yielding consistent gains in prediction and robustness.
Abstract
Long-video question answering is challenging since the answer often hinges on a few decisive moments scattered throughout the video, while memory constraints force Multimodal Large Language Models (MLLMs) to sample frames at extremely low rates, resulting in sparsity that risks omitting key evidence. Though aggressively enlarging the context size is intuitive, we argue that performance remains fundamentally constrained by the bias, \emph{i.e.}, the misleading cues caused by spurious \textit{linguistic} correlations and salient yet irrelevant \textit{visual} observations. In this paper, we first introduce {S-MME}, a benchmark designed to systematically diagnose shortcut-biased behavior in MLLMs. To mitigate this failure, we further propose a training-free framework, Counterfactual Long-video Evidence-Aware Reasoning (CLEAR). By treating the full video-question pair as a complete view, CLEAR estimates bias effects via augmented views by only keeping the question or locally salient visual clips. Then, we intervene hidden states to mitigate the discrepancy at inference such that the correct answer can be predicted confidently. With experimental studies across five benchmarks, we show that our method is generalizable and can be integrated in different MLLMs, yielding consistent gains in prediction and robustness. We hope CLEAR can offer a complementary direction in test-time scaling for long-video understanding.
Large Vision-Language Models (LVLMs) demonstrate strong performance on multiple-choice question answering (MCQA), yet their reliability under biased conditions remains underexplored. We investigate length bias, the systematic preference for longer answer options, through controlled benchmarks spanning fine-grained visu...
Md. Atabuzzaman, Hani Alomari, Chris Thomas· Proceedings of the 2026 Conf...· 0 citations
Video multimodal large language models (MLLMs) keep climbing video question answering benchmarks, yet shuffling the frames, masking the segment that supports the answer, or occluding the target object barely changes their predictions. The accuracy rests on appearance and language priors, not on the temporal evidence th...
Zhaolu Kang, Shi-Yu Liu, Tai-Long Luo et al.· 0 citations
In tri-modal visual question answering (VQA), auxiliary text is commonly used to complement visual and textual inputs, yet its reliability is often uncontrolled. While prior work studies modality conflicts in general, it remains unclear how different types of unreliable auxiliary text affect answer selection under fixe...
Tam Le Thi Thanh, Van Tran Hoang, Hong-Hanh Nguyen-Le et al.· Proceedings of the 34th ACM...· 0 citations
The hardest part of understanding a long video is not pinpointing any one moment but synthesizing many, e.g., answering a question that requires tracking what develops across hours of content and articulating how the pieces fit together. To date, most long-video QA datasets require only a short answer or a multiple-cho...
Shaden Shaar, Bradon Thymes, Majd Aldaye et al.· 0 citations
VideoMM is introduced, which marks a paradigm shift from model-centric downsizing to adaptive perceptual granularity and accelerates inference by 2.73 times over current leading methods, establishing a highly scalable paradigm for long-video understanding.
A novel training framework that enhances counterfactual contrastive learning for VQA and introduces a three-stage curriculum for stable multi-objective optimization, an enhanced Batch-Contrastive loss for more discriminative feature learning and two novel regularizers.
Truong-Binh Duong, T. Tran, Ngoc-Thao Nguyen et al.· Procedia Computer Science· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.