MotionHalluc is a benchmark designed to evaluate motion hallucinations in cross‑video comparison tasks, consisting of 1,540 fine‑grained questions over 553 video pairs. It assesses hallucinations across three dimensions—directional, attributional, and temporal—and reveals that current large multimodal models are highly susceptible to these errors. The authors also introduce a training‑free Perceive‑Parse‑Verify baseline that injects explicit kinematic measurements, achieving an average 10.6% performance improvement across models.
arXiv:2609.09895v1 Announce Type: new Abstract: Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model...
arXiv:2609.36440v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have recently achieved remarkable progress across multimodal tasks, yet object hallucination remains a persistent...
arXiv:2611.06433v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post...
Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post-training methods constructs visual contrasts thr...
Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model hallucinations, and heterogeneous mechanisms mak...
arXiv:2601. 22574v2 Announce Type: replace-cross Abstract: Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination.
The paper examines six inference-time hallucination mitigation methods applied to three large vision-language models across four benchmarks, including MMStar. It finds that reducing hallucination rates often comes at the cost of lower informativeness—such as decreased object recall, visual coverage, and response detail—and that gains on hallucination benchmarks do not consistently translate to improved performance on fine-grained perception and reasoning tasks. The authors argue that current evaluation protocols may overstate progress by favoring conservative generation, and propose that hallucination mitigation should be assessed as a trade-off among faithfulness, informativeness, and overall capability.
arXiv:2602. 01740v3 Announce Type: replace Abstract: Video language models (Video-LLMs) are prone to hallucinations, generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased.
arXiv:2610.02976v1 Announce Type: new Abstract: Audio-Visual Large Language Models (AV-LLMs) remain prone to cross-modal hallucinations, where one modality incorrectly affects predictions about anoth...
The paper examines how hallucinations arise in multi-stage video‑understanding agents by aligning existing benchmarks with the stages of temporal grounding, visual observation, and reasoning. It introduces a causal stage‑intervention protocol that isolates each stage while keeping the downstream task constant, revealing that grounding errors dominate downstream hallucinations and that correct region location matters more than precise temporal overlap. The study also shows that current benchmark scores poorly predict causal sensitivity and can fail under distribution shift, advocating for stage‑aware evaluation methods.
arXiv:2606. 29531v1 Announce Type: cross Abstract: We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs.
The paper introduces Dynamic Alignment Compensation (DAC), a training‑free inference‑time technique designed to reduce hallucinations in Large Vision‑Language Models (LVLMs). DAC monitors cross‑modal representation drift across decoder layers and generation steps, applying lightweight residual compensation through Layer‑wise Semantic Compensation and Sequential Semantic Correction. Experiments on nine multimodal benchmarks across various LVLM backbones demonstrate that DAC consistently lowers hallucination rates while preserving overall performance.