Follow
Xinxi Lyu
Xinxi Lyu
Allen Institute for Artificial Intelligence
Verified email at allenai.org - Homepage
Title
Cited by
Cited by
Year
Rethinking the role of demonstrations: What makes in-context learning work?
S Min, X Lyu, A Holtzman, M Artetxe, M Lewis, H Hajishirzi, L Zettlemoyer
arXiv preprint arXiv:2202.12837, 2022
9172022
Factscore: Fine-grained atomic evaluation of factual precision in long form text generation
S Min, K Krishna, X Lyu, M Lewis, W Yih, PW Koh, M Iyyer, L Zettlemoyer, ...
arXiv preprint arXiv:2305.14251, 2023
2322023
Dolma: An open corpus of three trillion tokens for language model pretraining research
L Soldaini, R Kinney, A Bhagia, D Schwenk, D Atkinson, R Authur, ...
arXiv preprint arXiv:2402.00159, 2024
44*2024
Prompt waywardness: The curious case of discretized interpretation of continuous prompts
D Khashabi, S Lyu, S Min, L Qin, K Richardson, S Welleck, H Hajishirzi, ...
arXiv preprint arXiv:2112.08348, 2021
40*2021
Z-icl: Zero-shot in-context learning with pseudo-demonstrations
X Lyu, S Min, I Beltagy, L Zettlemoyer, H Hajishirzi
arXiv preprint arXiv:2212.09865, 2022
392022
The system can't perform the operation now. Try again later.
Articles 1–5