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.
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: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: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:2606. 26904v1 Announce Type: cross Abstract: Video reasoning language models implicitly assume that every input frame is equally reliable.
arXiv:2609.37950v1 Announce Type: new Abstract: Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However,...
arXiv:2606. 27596v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination.
arXiv:2609.16646v1 Announce Type: new Abstract: When strong multimodal models are widely available, progress requires new scientific methodologies beyond benchmark scores---using models as instrument...
The paper introduces REVEAL, a diagnostic benchmark that stresses Video‑Language Models (VidLMs) on five controlled probes—camera‑motion sensitivity, cross‑frame integration, video sycophancy, language‑only shortcuts, and temporal expectation bias—to assess how well these models encode and use visual evidence. Experiments on 12 VidLMs reveal systematic failures: some visual signals are never reliably encoded, while others are overridden by model priors, leading to performance below chance on several probes that humans solve with high accuracy. Mechanistic probes further pinpoint where and why visual evidence is lost, demonstrating that under assertive prompts a model’s output becomes nearly invariant to real versus random video input, rendering visual evidence causally inert.
arXiv:2601. 07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches.
arXiv:2606. 27922v1 Announce Type: cross Abstract: Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal parameters.
arXiv:2609.40048v1 Announce Type: new Abstract: Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget,...
arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a...