Mitigating fine-grained hallucination by fine-tuning large vision-language models with caption rewrites

• Main Authors: WANG, Lei, HE, Jiabang, LI, Shenshen, LIU, Ning, LIM, Ee-peng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Hallucination Mitigation; Large Vision-Language Models; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8750; https://ink.library.smu.edu.sg/context/sis_research/article/9753/viewcontent/MitigatingFine_GrainedHallucination_av.pdf
• Institution: Singapore Management University

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 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 Fine-Grained Object Hallucination Evaluation (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.