EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912551120404480 |
|---|---|
| author | Seth, Ashish Tyagi, Utkarsh Selvakumar, Ramaneswaran Anand, Nishit Kumar, Sonal Ghosh, Sreyan Duraiswami, Ramani Agarwal, Chirag Manocha, Dinesh |
| author_facet | Seth, Ashish Tyagi, Utkarsh Selvakumar, Ramaneswaran Anand, Nishit Kumar, Sonal Ghosh, Sreyan Duraiswami, Ramani Agarwal, Chirag Manocha, Dinesh |
| contents | Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in complex multimodal tasks. While MLLMs excel at visual perception and reasoning in third-person and egocentric videos, they are prone to hallucinations, generating coherent yet inaccurate responses. We present EgoIllusion, a first benchmark to evaluate MLLM hallucinations in egocentric videos. EgoIllusion comprises 1,400 videos paired with 8,000 human-annotated open and closed-ended questions designed to trigger hallucinations in both visual and auditory cues in egocentric videos. Evaluations across ten MLLMs reveal significant challenges, including powerful models like GPT-4o and Gemini, achieving only 59% accuracy. EgoIllusion lays the foundation in developing robust benchmarks to evaluate the effectiveness of MLLMs and spurs the development of better egocentric MLLMs with reduced hallucination rates. Our benchmark will be open-sourced for reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding Seth, Ashish Tyagi, Utkarsh Selvakumar, Ramaneswaran Anand, Nishit Kumar, Sonal Ghosh, Sreyan Duraiswami, Ramani Agarwal, Chirag Manocha, Dinesh Artificial Intelligence Computer Vision and Pattern Recognition Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in complex multimodal tasks. While MLLMs excel at visual perception and reasoning in third-person and egocentric videos, they are prone to hallucinations, generating coherent yet inaccurate responses. We present EgoIllusion, a first benchmark to evaluate MLLM hallucinations in egocentric videos. EgoIllusion comprises 1,400 videos paired with 8,000 human-annotated open and closed-ended questions designed to trigger hallucinations in both visual and auditory cues in egocentric videos. Evaluations across ten MLLMs reveal significant challenges, including powerful models like GPT-4o and Gemini, achieving only 59% accuracy. EgoIllusion lays the foundation in developing robust benchmarks to evaluate the effectiveness of MLLMs and spurs the development of better egocentric MLLMs with reduced hallucination rates. Our benchmark will be open-sourced for reproducibility. |
| title | EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.12687 |