Generating Synthetic Data with
Large Language Models for
Low-Resource Sentence Retrieval

(TPDL 2025)

This repository contains the reference code and models for "Generating Synthetic Data with Large Language Models for Low-Resource Sentence Retrieval".

TODO

Source code and trained model will be released soon.

Citation

Please cite with the following BibTeX:

@inproceedings{caffagni2025generating,
  title={{Generating Synthetic Data with Large Language Models for Low-Resource Sentence Retrieval}},
  author={Caffagni, Davide and Cocchi, Federico and Mambelli, Anna and Tutrone, Fabio and Zanella, Marco and Cornia, Marcella and Cucchiara, Rita},
  booktitle={International Conference on Theory and Practice of Digital Libraries},
  year={2025}
}