# VideoHEDGE: Entropy-Based Hallucination Detection for Video-VLMs via Semantic Clustering and Spatiotemporal Perturbations

arXiv: https://arxiv.org/abs/2601.08557 · HTML: https://mlsanity.com/paper/2601.08557/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 16 of 16)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos](https://mlsanity.com/paper/1804.04527/) (2018)
- [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020)
- [A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models](https://mlsanity.com/paper/2405.09589/) (2024)
- [SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models](https://mlsanity.com/paper/2403.02509/) (2024)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs](https://mlsanity.com/paper/2503.05980/) (2025)
- [Enhancing Temporal Modeling of Video LLMs via Time Gating](https://mlsanity.com/paper/2410.05714/) (2024)
- [Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations](https://mlsanity.com/paper/2410.15359/) (2024)
- [Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding](https://mlsanity.com/paper/2505.03788/) (2025)
- [SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding](https://mlsanity.com/paper/2505.16630/) (2025)

## Built on by (most cited first, 1 of 1)

- [Target-Checked Reliability Score Refinement for Video Question Answering](https://mlsanity.com/paper/2609.13288/) (2026)

## Abstract (arXiv)

Hallucinations in video-capable vision-language models (Video-VLMs) remain frequent and high-confidence, while existing uncertainty metrics often fail to align with correctness. We introduce VideoHEDGE, a modular framework for hallucination detection in video question answering that extends entropy-based reliability estimation from images to temporally structured inputs. Given a video-question pair, VideoHEDGE draws a baseline answer and multiple high-temperature generations from both clean clips and photometrically and spatiotemporally perturbed variants, then clusters the resulting textual outputs into semantic hypotheses using either Natural Language Inference (NLI)-based or embedding-based methods. Cluster-level probability masses yield three reliability scores: Semantic Entropy (SE), RadFlag, and Vision-Amplified Semantic Entropy (VASE). We evaluate VideoHEDGE on the SoccerChat benchmark using an LLM-as-a-judge to obtain binary hallucination labels. Across three 7B Video-VLMs (Qwen2-VL, Qwen2.5-VL, and a SoccerChat-finetuned model), VASE consistently achieves the highest ROC-AUC, especially at larger distortion budgets, while SE and RadFlag often operate near chance. We further show that embedding-based clustering matches NLI-based clustering in detection performance at substantially lower computational cost, and that domain fine-tuning reduces hallucination frequency but yields only modest improvements in calibration. The hedge-bench PyPI library enables reproducible and extensible benchmarking, with full code and experimental resources available at https://github.com/Simula/HEDGE#videohedge .