Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Agrawal, H., et al.: nocaps: novel object captioning at scale. In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV, pp. 8947–8956. IEEE (2019)
Bang, Y., et al.: A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. CoRR abs/2302.04023 (2023). https://doi.org/10.48550/arXiv.2302.04023. https://doi.org/10.48550/arXiv.2302.04023
Biten, A.F., Gómez, L., Karatzas, D.: Let there be a clock on the beach: educing object hallucination in image captioning. In: IEEE/CVF Winter Conference on Applications of Computer Vision, WACV (2022)
Brown, T.B., et al.: Language models are few-shot learners. In: NeurIPS (2020)
Chung, H.W., et al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)
Dai, W., et al.: Instructblip: Towards general-purpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500 (2023)
Gong, T., et al.: Multimodal-gpt: A vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790 (2023)
Huang, Y., Feng, X., Feng, X., Qin, B.: The factual inconsistency problem in abstractive text summarization: a survey. arXiv preprint arXiv:2104.14839 (2021)
Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1–38 (2023)
Lee, S., Park, S.H., Jo, Y., Seo, M.: Volcano: mitigating multimodal hallucination through self-feedback guided revision. arXiv preprint arXiv:2311.07362 (2023)
Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888–12900. PMLR (2022)
Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)
Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Aligning large multi-modal model with robust instruction tuning. arXiv preprint arXiv:2306.14565 (2023)
Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)
Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: The 36th Conference on Neural Information Processing Systems (NeurIPS) (2022)
Maynez, J., Narayan, S., Bohnet, B., McDonald, R.: On faithfulness and factuality in abstractive summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1906–1919 (2020)
OpenAI: Introducing chatgpt (2022). https://openai.com/blog/chatgpt
OpenAI: GPT-4 technical report. CoRR abs/2303.08774 (2023)
Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., Yang, D.: Is chatgpt a general-purpose natural language processing task solver? arXiv preprint arXiv:2302.06476 (2023)
Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: EMNLP (2018)
Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-OKVQA: a benchmark for visual question answering using world knowledge. In: ECCV 2022, vol. 13668, pp. 146–162. Springer (2022)
Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: solving AI tasks with chatgpt and its friends in huggingface. CoRR abs/2303.17580 (2023)
Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. EMNLP (2021)
Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)
Wang, J., et al.: An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)
Wang, J., et al.: Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126 (2023)
Wang, Y., et al.: Self-instruct: aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560 (2022)
Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatgpt: talking, drawing and editing with visual foundation models. CoRR abs/2303.04671 (2023)
Wu, Z., et al.: A controllable model of grounded response generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35 (2021)
Xiao, Y., Wang, W.Y.: On hallucination and predictive uncertainty in conditional language generation. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 2734–2744 (2021)
Xu, P., et al.: Lvlm-ehub: a comprehensive evaluation benchmark for large vision-language models (2023)
Xu, Z., Shen, Y., Huang, L.: Multiinstruct: improving multi-modal zero-shot learning via instruction tuning. arXiv preprint arXiv:2212.10773 (2022)
Yang, Z., et al.: MM-REACT: prompting chatgpt for multimodal reasoning and action. CoRR abs/2303.11381 (2023)
Ye, Q., et al.: mplug-owl: modularization empowers large language models with multimodality (2023)
Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models. arXiv preprint arXiv:2310.16045 (2023)
Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, L., He, J., Li, S., Liu, N., Lim, EP. (2024). Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites. In: Rudinac, S., et al. MultiMedia Modeling. MMM 2024. Lecture Notes in Computer Science, vol 14557. Springer, Cham. https://doi.org/10.1007/978-3-031-53302-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-53302-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53301-3
Online ISBN: 978-3-031-53302-0
eBook Packages: Computer ScienceComputer Science (R0)