InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4

Lai Wei, Zihao Jiang, Weiran Huang, Lichao Sun

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Multimodal LLM, Instruction Curation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce InstructionGPT-4, which is fine-tuned on 200 selected samples with high quality.

Abstract:

Multimodal large language models are typically trained in two stages: first pre-training on image-text pairs, and then fine-tuning using supervised vision-language instruction data.
Recent studies have shown that large language models can achieve satisfactory results even with a limited amount of high-quality instruction-following data.
In this paper, we introduce InstructionGPT-4, which is fine-tuned on a small dataset comprising only 200 examples, amounting to approximately 6% of the instruction-following data used in the alignment dataset for MiniGPT-4.
To achieve this, we first propose several metrics to access the quality of multimodal instruction data.
Based on these metrics, we present an effective and trainable data selector to automatically identify and filter low-quality vision-language data.
By employing this method, InstructionGPT-4 outperforms the original MiniGPT-4 on various evaluations.
Overall, our findings demonstrate that less but high-quality instruction tuning data is efficient in enabling multimodal large language models to generate better output.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2243