Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites
Wang, Lei, He, Jiabang, Li, Shenshen, Liu, Ning, Lim, Ee-Peng
–arXiv.org Artificial Intelligence
Large language models (LLMs) have shown remarkable performance in natural language processing (NLP) tasks. To comprehend and execute diverse human instructions over image data, instruction-tuned large vision-language models (LVLMs) have been introduced. However, LVLMs may suffer from different types of object hallucinations. Nevertheless, LVLMs are evaluated for coarse-grained object hallucinations only (i.e., generated objects non-existent in the input image). The fine-grained object attributes and behaviors non-existent in the image may still be generated but not measured by the current evaluation methods. In this paper, we thus focus on reducing fine-grained hallucinations of LVLMs. We propose \textit{ReCaption}, a framework that consists of two components: rewriting captions using ChatGPT and fine-tuning the instruction-tuned LVLMs on the rewritten captions. We also propose a fine-grained probing-based evaluation method named \textit{Fine-Grained Object Hallucination Evaluation} (\textit{FGHE}). Our experiment results demonstrate that ReCaption effectively reduces fine-grained object hallucination for different LVLM options and improves their text generation quality. The code can be found at https://github.com/Anonymousanoy/FOHE.
arXiv.org Artificial Intelligence
Dec-4-2023
- Country:
- Asia
- China (0.14)
- Middle East > Israel (0.14)
- North America > United States (0.14)
- Asia
- Genre:
- Research Report > New Finding (0.48)
- Industry:
- Leisure & Entertainment > Sports
- Tennis (0.69)
- Transportation > Air (0.68)
- Leisure & Entertainment > Sports
- Technology: