InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval

Built on

Adafactor: Adaptive learning rates with sublinear memory cost
N. Shazeer and M. Stern · 2018
Earlier work this paper cites.
Retrieval of the best counterargument without prior topic knowledge
H. Wachsmuth, S. Syed, and B. Stein · 2018
Earlier work this paper cites.
Document ranking with a pretrained sequence-to-sequence model
R. Nogueira, Z. Jiang, R. Pradeep, and J. Lin · 2020
Earlier work this paper cites.
Pyserini: An easy-to-use python toolkit to support replicable ir research with sparse and dense representations
Original
J. Lin, X. Ma, S.-C. Lin, J.-H. Yang, R. Pradeep, and R. Nogueira · 2021
Earlier work this paper cites.

Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models
Original
N. Thakur, N. Reimers, A. Rücklé, A. Srivastava, and I. Gurevych · 2021
Cited alongside, same era.
GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model
B. Wang and A. Komatsuzaki · 2021
Cited alongside, same era.
Finetuned language models are zero-shot learners
Original
J. Wei, M. Bosma, V. Y. Zhao, K. Guu, A. W. Yu, B. Lester, N. Du, A. M. Dai, and Q. V. Le · 2021
Cited alongside, same era.

Inpars: Data augmentation for information retrieval using large language models
Original
L. Bonifacio, H. Abonizio, M. Fadaee, and R. Nogueira · 2022
Later among the works it cites.
Promptagator: Few-shot dense retrieval from 8 examples
Original
Z. Dai, V. Y. Zhao, J. Ma, Y. Luan, J. Ni, J. Lu, A. Bakalov, K. Guu, K. B. Hall, and M.-W. Chang · 2022
Later among the works it cites.
Rankt5: Fine-tuning t5 for text ranking with ranking losses
Original
H. Zhuang, Z. Qin, R. Jagerman, K. Hui, J. Ma, J. Lu, J. Ni, X. Wang, and M. Bendersky · 2022
Later among the works it cites.