Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913342233247744 |
|---|---|
| author | Zhang, Huixuan Zhang, Junzhe Wan, Xiaojun |
| author_facet | Zhang, Huixuan Zhang, Junzhe Wan, Xiaojun |
| contents | Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas. Nevertheless, these models frequently experience significant issues with generating inaccurate information, which is hallucination. In this study, we concentrate on a specific type of hallucination-number hallucination, referring to models incorrectly identifying the number of certain objects in pictures. We perform quantitative evaluations regarding number hallucination, showing it to be critical in major open-source large vision-language models. Furthermore, we utilizes two related tasks to conduct an in-depth analysis of number hallucination, revealing the severe inner and outer inconsistency among all tasks. Based on this examination, we devise a training approach aimed at improving consistency to reduce number hallucinations, which leads to an 8% enhancement in performance over direct finetuning methods. Our code and dataset will be released to the community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01373 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models Zhang, Huixuan Zhang, Junzhe Wan, Xiaojun Computation and Language Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas. Nevertheless, these models frequently experience significant issues with generating inaccurate information, which is hallucination. In this study, we concentrate on a specific type of hallucination-number hallucination, referring to models incorrectly identifying the number of certain objects in pictures. We perform quantitative evaluations regarding number hallucination, showing it to be critical in major open-source large vision-language models. Furthermore, we utilizes two related tasks to conduct an in-depth analysis of number hallucination, revealing the severe inner and outer inconsistency among all tasks. Based on this examination, we devise a training approach aimed at improving consistency to reduce number hallucinations, which leads to an 8% enhancement in performance over direct finetuning methods. Our code and dataset will be released to the community. |
| title | Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.01373 |