Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.11824 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917478721912832 |
|---|---|
| author | Wu, Jialin Shi, Wei Shen, Han Qi, Peigui Tang, Kunsheng Huang, Zhicong Wang, Binghao Yang, Zhou |
| author_facet | Wu, Jialin Shi, Wei Shen, Han Qi, Peigui Tang, Kunsheng Huang, Zhicong Wang, Binghao Yang, Zhou |
| contents | Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper network layers. To address this, we propose REVIS, a training-free framework designed to explicitly re-activate this suppressed visual information. Rooted in latent space geometry, REVIS extracts the pure visual information vector via orthogonal projection and employs a calibrated strategy to perform sparse intervention only at the precise depth where suppression occurs. This surgical approach effectively restores visual information with minimal computational cost. Empirical evaluations on standard benchmarks demonstrate that REVIS reduces object hallucination rates by approximately 19% compared to state-of-the-art baselines, while preserving general reasoning capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11824 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models Wu, Jialin Shi, Wei Shen, Han Qi, Peigui Tang, Kunsheng Huang, Zhicong Wang, Binghao Yang, Zhou Artificial Intelligence Machine Learning Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper network layers. To address this, we propose REVIS, a training-free framework designed to explicitly re-activate this suppressed visual information. Rooted in latent space geometry, REVIS extracts the pure visual information vector via orthogonal projection and employs a calibrated strategy to perform sparse intervention only at the precise depth where suppression occurs. This surgical approach effectively restores visual information with minimal computational cost. Empirical evaluations on standard benchmarks demonstrate that REVIS reduces object hallucination rates by approximately 19% compared to state-of-the-art baselines, while preserving general reasoning capabilities. |
| title | Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.11824 |