Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts
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_ | 1866915206461915136 |
|---|---|
| author | Rykov, Elisei Petrushina, Kseniia Titova, Kseniia Panchenko, Alexander Konovalov, Vasily |
| author_facet | Rykov, Elisei Petrushina, Kseniia Titova, Kseniia Panchenko, Alexander Konovalov, Vasily |
| contents | Quantifying the realism of images remains a challenging problem in the field of artificial intelligence. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein's death. We introduce a novel method for assessing image realism using Large Vision-Language Models (LVLMs) and Natural Language Inference (NLI). Our approach is based on the premise that LVLMs may generate hallucinations when confronted with images that defy common sense. Using LVLM to extract atomic facts from these images, we obtain a mix of accurate facts and erroneous hallucinations. We proceed by calculating pairwise entailment scores among these facts, subsequently aggregating these values to yield a singular reality score. This process serves to identify contradictions between genuine facts and hallucinatory elements, signaling the presence of images that violate common sense. Our approach has achieved a new state-of-the-art performance in zero-shot mode on the WHOOPS! dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15948 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts Rykov, Elisei Petrushina, Kseniia Titova, Kseniia Panchenko, Alexander Konovalov, Vasily Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Quantifying the realism of images remains a challenging problem in the field of artificial intelligence. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein's death. We introduce a novel method for assessing image realism using Large Vision-Language Models (LVLMs) and Natural Language Inference (NLI). Our approach is based on the premise that LVLMs may generate hallucinations when confronted with images that defy common sense. Using LVLM to extract atomic facts from these images, we obtain a mix of accurate facts and erroneous hallucinations. We proceed by calculating pairwise entailment scores among these facts, subsequently aggregating these values to yield a singular reality score. This process serves to identify contradictions between genuine facts and hallucinatory elements, signaling the presence of images that violate common sense. Our approach has achieved a new state-of-the-art performance in zero-shot mode on the WHOOPS! dataset. |
| title | Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.15948 |