AnReu/DSI-large-TriviaQA-QG

This repository contains one of the models analyzed in our paper Reverse-Engineering the Retrieval Process in GenIR Models.

Training

The model is based on T5-large and was trained on the TriviaQA dataset (with only generated questions as input) as a atomic GenIR model using the setup of DSI.

Model Overview

Model	Huggingface URL
NQ10k	DSI-large-NQ10k
NQ100k	DSI-large-NQ100k
NQ320k	DSI-large-NQ320k
Trivia-QA	DSI-large-TriviaQA
Trivia-QA QG	DSI-large-TriviaQA QG

Citation

@inproceedings{Reusch2025Reverse,
  author = {Reusch, Anja and Belinkov, Yonatan},
  title = {Reverse-Engineering the Retrieval Process in GenIR Models},
  year = {2025},
  isbn = {9798400715921},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3726302.3730076},
  doi = {10.1145/3726302.3730076},
  booktitle = {Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages = {668–677},
  numpages = {10},
  location = {Padua, Italy},
  series = {SIGIR '25}
}