Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding

Yihao Ding, Qiang Sun 0006, Puzhen Wu, Sirui Li, Siwen Luo, Wei Liu 0006. Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding. In Companion Proceedings of the ACM Web Conference 2026, WWW Companion 2026, Dubai, United Arab Emirates, 29 June 2026 - 3 July 2026. pages 124-127, ACM, 2026. [doi]

@inproceedings{DingSWLLL26,
  title = {Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding},
  author = {Yihao Ding and Qiang Sun 0006 and Puzhen Wu and Sirui Li and Siwen Luo and Wei Liu 0006},
  year = {2026},
  doi = {10.1145/3774905.3793117},
  url = {https://doi.org/10.1145/3774905.3793117},
  researchr = {https://researchr.org/publication/DingSWLLL26},
  cites = {0},
  citedby = {0},
  pages = {124-127},
  booktitle = {Companion Proceedings of the ACM Web Conference 2026, WWW Companion 2026, Dubai, United Arab Emirates, 29 June 2026 - 3 July 2026},
  publisher = {ACM},
  isbn = {979-8-4007-2308-7},
}