Visually Dehallucinative Instruction Generation: Know What You Don't Know
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_ | 1866916126269636608 |
|---|---|
| author | Cha, Sungguk Lee, Jusung Lee, Younghyun Yang, Cheoljong |
| author_facet | Cha, Sungguk Lee, Jusung Lee, Younghyun Yang, Cheoljong |
| contents | "When did the emperor Napoleon invented iPhone?" Such hallucination-inducing question is well known challenge in generative language modeling. In this study, we present an innovative concept of visual hallucination, referred to as "I Know (IK)" hallucination, to address scenarios where "I Don't Know" is the desired response. To effectively tackle this issue, we propose the VQAv2-IDK benchmark, the subset of VQAv2 comprising unanswerable image-question pairs as determined by human annotators. Stepping further, we present the visually dehallucinative instruction generation method for IK hallucination and introduce the IDK-Instructions visual instruction database. Our experiments show that current methods struggle with IK hallucination. Yet, our approach effectively reduces these hallucinations, proving its versatility across different frameworks and datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09717 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visually Dehallucinative Instruction Generation: Know What You Don't Know Cha, Sungguk Lee, Jusung Lee, Younghyun Yang, Cheoljong Computer Vision and Pattern Recognition "When did the emperor Napoleon invented iPhone?" Such hallucination-inducing question is well known challenge in generative language modeling. In this study, we present an innovative concept of visual hallucination, referred to as "I Know (IK)" hallucination, to address scenarios where "I Don't Know" is the desired response. To effectively tackle this issue, we propose the VQAv2-IDK benchmark, the subset of VQAv2 comprising unanswerable image-question pairs as determined by human annotators. Stepping further, we present the visually dehallucinative instruction generation method for IK hallucination and introduce the IDK-Instructions visual instruction database. Our experiments show that current methods struggle with IK hallucination. Yet, our approach effectively reduces these hallucinations, proving its versatility across different frameworks and datasets. |
| title | Visually Dehallucinative Instruction Generation: Know What You Don't Know |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.09717 |