https://github.com/thunlp-mt/fiig

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions (EMNLP 2023 Findings)
https://github.com/thunlp-mt/fiig

Last synced: 7 months ago
JSON representation

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions (EMNLP 2023 Findings)

• Host: GitHub
• URL: https://github.com/thunlp-mt/fiig
• Owner: THUNLP-MT
• License: mit
• Created: 2023-10-18T15:33:49.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-11-21T02:51:20.000Z (over 2 years ago)
• Last Synced: 2024-12-31T05:18:56.119Z (over 1 year ago)
• Size: 671 KB
• Stars: 8
• Watchers: 5
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
This is the repo for "Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions" (EMNLP 2023 Findings) [paper](https://arxiv.org/abs/2311.11598)

![pipeline](./images/framework-cameraready.png )

# Installation

coming soon

# Examples

coming soon

# Bibtex

If you find our projects helpful to your research, please consider citing:

```

@misc{wang2023filling,

      title={Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions},

      author={Ziyue Wang and Chi Chen and Peng Li and Yang Liu},

      year={2023},

      eprint={2311.11598},

      archivePrefix={arXiv},

      primaryClass={cs.CL}

}

```