HarmVideoBench: Multi-layered benchmark for harmful video understanding in large multimodal models
Researchers introduce HarmVideoBench, a diagnostic benchmark of 1,379 videos paired with 4,137 multiple-choice questions designed to evaluate harmful video understanding across three hierarchical dimensions: Observable Evidence, Clip-Internal Meaning, and Beyond-Clip Reasoning. The benchmark addresses limitations in existing work by moving beyond binary classification and requiring explanatory rationales. The authors evaluate 19 leading models and introduce BCR, a method that dynamically retrieves context based on predicted reasoning boundaries, improving macro average performance from 61.7% to 84.4%.
Related guides (3)
Related events (8)
PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning in MLLMs
PaSBench-Video is a 740-video benchmark designed to evaluate whether multimodal large language models can issue timely, accurate safety warnings during the window between a visible danger sign and an accident. Videos span four domains (driving, healthcare, daily life, industrial production) and are annotated with frame-level risk onset and accident boundaries, requiring causal temporal reasoning rather than static scene classification. Testing 13 MLLMs reveals no model exceeds 20% on the strictest metric, with recall strongly coupled to false-positive rate (Pearson r=0.64), indicating models rely on scene-level activity cues rather than genuine hazard reasoning. Performance varies sharply by domain, with driving being particularly problematic due to visual similarity between routine and hazardous scenes.
Evaluating Audio Reasoning with Big Bench Audio
Hugging Face introduces Big Bench Audio, a new benchmark designed to evaluate audio reasoning capabilities in AI models. The benchmark appears to extend the Big Bench evaluation framework into the audio domain, targeting multimodal models that process and reason over audio inputs. This release addresses a gap in evaluation tooling for audio-capable language models.
Survey: Human-View Video Understanding with MLLMs — Watch, Remember, Reason Framework
A new arXiv survey paper proposes a unified 'human-view' framework for analyzing multimodal LLM-based video understanding, organized around three functional abilities: watching (perception), remembering (memory), and reasoning. The authors introduce a formulation characterizing video understanding systems by perceptual representations, memory states, reasoning traces, and predictions, then survey methods, datasets, and benchmarks across these dimensions. The work covers challenges including spatio-temporal perception, long-video processing, streaming understanding, and faithful reasoning, with application domains spanning egocentric, sports, medical, and narrative video.
Moment-Video: Benchmark Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
Moment-Video is a new benchmark of 1,000 human-verified video-QA pairs designed to evaluate how well video multimodal large language models (MLLMs) handle brief, localized visual events that may span only a few frames. The benchmark covers 7 domains and 25 subcategories across four task types: Temporal Occurrence, Temporal Counting, Action Description, and Temporal Reasoning. Evaluation of 33 proprietary and open-source models reveals severe deficiencies: the best model (Seed-2.0-Pro) achieves only 39.6% accuracy, while most open-source models score below 25%. Diagnostic analyses show that denser frame sampling helps but does not resolve the bottleneck, pointing to fundamental limitations in how current video MLLMs represent and preserve transient visual evidence.
Benchmark for view-level visual evidence identification in multi-view MLLMs for autonomous driving
A new arXiv preprint introduces a multi-view visual question answering benchmark targeting evidence-source identification in autonomous driving scenarios. Given six synchronized NuScenes camera views and a question, models must identify which camera view supports the answer — not just produce a correct answer. The 122-pair benchmark spans causality, counterfactual reasoning, and intent prediction, and exposes grounding failures that answer-only evaluation misses. The work addresses a meaningful gap between answer accuracy and correct visual grounding in safety-critical multimodal systems.
Introducing ConTextual: Benchmark for Joint Text-Image Reasoning in Text-Rich Scenes
Hugging Face introduces ConTextual, a new benchmark evaluating multimodal models on their ability to jointly reason over text and images in text-rich scenes. The benchmark targets a specific capability gap where models must integrate visual and textual information simultaneously rather than treating them independently. A leaderboard accompanies the benchmark to track model progress on this task.
HarmAmp Benchmark and TrajSafe Monitor for Multi-Turn Harm Amplification in LLMs
This paper introduces HarmAmp, a benchmark covering twelve risk categories designed to evaluate how LLMs compound harm across multi-turn conversations, addressing two threat vectors: democratizing specialized harmful expertise and scaling harmful operations. The authors also propose TrajSafe, a proactive monitoring system that anticipates harmful conversational trajectories and intervenes by probing user intent or steering toward safer outputs. Experiments show TrajSafe reduces multi-turn harmfulness while maintaining low over-refusal rates and preserving general model capabilities. The work highlights a gap in existing safety research that focuses on single-turn evaluations rather than extended interaction dynamics.
TriViewBench: Controlled benchmark reveals fundamental multi-view spatial reasoning failures in MLLMs
Researchers introduce TriViewBench, a synthetic 3D benchmark of 1,923 scenes and 14K+ QA pairs designed to probe multi-view structural reasoning in MLLMs under controlled complexity scaling. Evaluating 18 open- and closed-source models, the study finds a universal capability hierarchy (Local Decision > Object Counting > Global Recovery) with severe performance collapse on Global Recovery tasks (80% relative drop at highest complexity). Chain-of-Thought prompting provides near-zero benefit, suggesting the bottleneck is cross-view spatial representation rather than reasoning strategy. The work identifies two mechanistically distinct failure modes in object counting: occlusion blindness causing undercounting in single-view tasks and cross-view identity confusion causing overcounting in multi-view tasks.