MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models

• URL: http://arxiv.org/abs/2607.01117v1
• Date: Wed, 01 Jul 2026 16:04:24 GMT
• Title: MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models
• Abstract summary: We present MoHallBench, a benchmark for diagnosing motion hallucination in VideoLLMs.<n>MoHallBench systematically evaluates three major sources of hallucination: co-occurrence priors, sequential inference, and similarity confusion.
• Score: 40.92844894741183
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Large Language Models (VideoLLMs) have shown strong progress in video understanding, yet they still suffer from hallucinations that are inconsistent with visual evidence. Existing benchmarks mainly focus on object hallucination or coarse action perception, leaving a key video-specific problem underexplored: motion hallucination, in which models infer human motions that are absent from the video. We present MoHallBench, a benchmark for diagnosing motion hallucination in VideoLLMs. MoHallBench systematically evaluates three major sources of hallucination: co-occurrence priors, sequential inference, and similarity confusion. It contains 11,306 video clips and 40,493 question-answer pairs, covering binary-choice, multiple-choice, and generative settings. We further introduce a bi-directional questioning protocol with bias-aware metrics to reduce affirmation bias in binary evaluation. Experiments on ten recent open-source VideoLLMs reveal a clear decoupling between action recognition and hallucination resistance, as models that perform well on positive action recognition often fail on adversarial negatives. Among all settings, sequential inference hallucination is the most severe, showing that current models tend to over-infer expected outcomes from partial motion cues. Our analyses further confirm that stronger priors and finer-grained similarity substantially amplify hallucination. We hope MoHallBench can facilitate future evaluation and mitigation of motion hallucination in VideoLLMs.

Related papers

• MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning [4.895176146260259]
  We introduce MotionHalluc, a benchmark for evaluating motion hallucinations in paired-video comparison.<n> MotionHalluc comprises 1540 fine-grained questions over 553 video pairs, evaluating hallucinations along three core dimensions: (1) hallucination, (2)attributional hallucination, and (3)temporal hallucination.<n>Our results show that motion reasoning with explicit quantitative measurements is a key factor in reducing hallucinations in cross-video comparison.
  arXiv  Detail & Related papers  (2026-06-22T09:13:19Z)
• SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding [30.820850789099932]
  We propose a training-free method that adaptively enhances temporal and spatial faithfulness for each output token.<n>SEASON outperforms all existing training-free hallucination mitigation approaches on three hallucination examination benchmarks.
  arXiv  Detail & Related papers  (2025-12-04T10:17:20Z)
• Alternating Perception-Reasoning for Hallucination-Resistant Video Understanding [35.20942192333083]
  We introduce a new framework that integrates a loop-based paradigm with an anti-hallucination reward.<n>Instead of describing the video at once, each loop requires the model to describe a video segment with precise timestamps.<n>For the risk of hallucinations, the Factual-Aware Evaluator evaluates each perception result as a reliable anti-hallucination reward.
  arXiv  Detail & Related papers  (2025-11-23T14:14:14Z)
• MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models [56.49314029765706]
  We introduce MESH, a benchmark designed to evaluate hallucinations in LVMs systematically.<n>MESH uses a Question-Answering framework with binary and multi-choice formats incorporating target and trap instances.<n>We demonstrate that MESH offers an effective and comprehensive approach for identifying hallucinations in videos.
  arXiv  Detail & Related papers  (2025-09-10T12:34:07Z)
• ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding [61.526407756322264]
  We introduce ELV-Halluc, the first benchmark dedicated to long-video hallucination.<n>We find that models are more prone to SAH on rapidly changing semantics.<n>We also achieve improvements on both ELV-Halluc and Video-MME.
  arXiv  Detail & Related papers  (2025-08-29T10:25:03Z)
• Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation [49.885797244626694]
  hallucination of large multimodal models (LMMs) provides responses that appear correct but are actually incorrect.<n>This paper aims to study the hallucination problem of LMMs in video modality, which is dynamic and more challenging compared to static modalities like images and text.
  arXiv  Detail & Related papers  (2025-03-25T13:12:17Z)
• Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer [51.7407540261676]
  We investigate a distinct type of hallucination, where a model can consistently answer a question correctly, but a seemingly trivial perturbation causes it to produce a hallucinated response with high certainty.<n>This phenomenon is particularly concerning in high-stakes domains such as medicine or law, where model certainty is often used as a proxy for reliability.<n>We show that CHOKE examples are consistent across prompts, occur in different models and datasets, and are fundamentally distinct from other hallucinations.
  arXiv  Detail & Related papers  (2025-02-18T15:46:31Z)
• EventHallusion: Diagnosing Event Hallucinations in Video LLMs [42.66453293963568]
  Multimodal Large Language Models (MLLMs) have made significant progress in the video comprehension field.<n>We propose EventHallusion, a novel benchmark that focuses on assessing the VideoLLMs' hallucination toward event.<n>We also propose a simple yet effective method, called Temporal Contrastive Decoding (TCD), to tackle the hallucination problems of VideoLLMs.
  arXiv  Detail & Related papers  (2024-09-25T03:49:46Z)
• VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models [59.05674402770661]
  This work introduces VideoHallucer, the first comprehensive benchmark for hallucination detection in large video-language models (LVLMs) VideoHallucer categorizes hallucinations into two main types: intrinsic and extrinsic, offering further subcategories for detailed analysis.
  arXiv  Detail & Related papers  (2024-06-24T06:21:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.