Reducing Hallucinations in Vision-Language Models via Latent Space Steering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913559005364224 |
|---|---|
| author | Liu, Sheng Ye, Haotian Xing, Lei Zou, James |
| author_facet | Liu, Sheng Ye, Haotian Xing, Lei Zou, James |
| contents | Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs. This paper investigates the underlying mechanisms of hallucination, focusing on the unique structure of LVLMs that distinguishes them from large language models (LLMs). We identify that hallucinations often arise from the sensitivity of text decoders to vision inputs, a natural phenomenon when image encoders and text decoders are pre-trained separately. Inspired by this, we introduce Visual and Textual Intervention (VTI), a novel technique designed to reduce hallucinations by steering latent space representations during inference to enhance the stability of vision features. As a task-agnostic test-time intervention, VTI can be easily applied to any problem without additional cost. Extensive experiments demonstrate that it can effectively reduce hallucinations and outperform baseline methods across multiple metrics, highlighting the critical role of vision feature stability in LVLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15778 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reducing Hallucinations in Vision-Language Models via Latent Space Steering Liu, Sheng Ye, Haotian Xing, Lei Zou, James Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs. This paper investigates the underlying mechanisms of hallucination, focusing on the unique structure of LVLMs that distinguishes them from large language models (LLMs). We identify that hallucinations often arise from the sensitivity of text decoders to vision inputs, a natural phenomenon when image encoders and text decoders are pre-trained separately. Inspired by this, we introduce Visual and Textual Intervention (VTI), a novel technique designed to reduce hallucinations by steering latent space representations during inference to enhance the stability of vision features. As a task-agnostic test-time intervention, VTI can be easily applied to any problem without additional cost. Extensive experiments demonstrate that it can effectively reduce hallucinations and outperform baseline methods across multiple metrics, highlighting the critical role of vision feature stability in LVLMs. |
| title | Reducing Hallucinations in Vision-Language Models via Latent Space Steering |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia |
| url | https://arxiv.org/abs/2410.15778 |