CASLIE-M

This repo contains the models for "Captions Speak Louder than Images (CASLIE): Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data"

CASLIE Models

The CASLIE-M model is instruction-tuned from the medium-size base model Mistral-7B-Instruct-v0.3.

Citation

@inproceedings{ling2025captions,
  title={Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data},
  author={Ling, Xinyi and Du, Hanwen and Peng, Bo and Zhu, Zhihui and Ning, Xia},
  booktitle={Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
  pages={743--768},
  year={2025}
}