Lost in the middle: How language models use long contexts

Record

Authors
Liu, N. F.; Lin, K.; Hewitt, J.; Paranjape, A.; Bevilacqua, M.; Petroni, F.; Liang, P.
Year
2023
Title
Lost in the middle: How language models use long contexts
Published in
arXiv
Type
Preprint
arXiv
arXiv:2307.03172
Our note
none yet
Verification
unverified: not yet checked against the source
Id
liu-2023-lost-middle-how-language-models-use

Cited on

As cited

The pages cite this work in one form.

  • Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P. (2023). Lost in the middle: How language models use long contexts. arXiv:2307.03172. (Source of the document-QA and key-value tasks; not read for this note.)

BibLaTeX

@misc{liu-2023-lost-middle-how-language-models-use,
  author = {Liu, N. F. and Lin, K. and Hewitt, J. and Paranjape, A. and Bevilacqua, M. and Petroni, F. and Liang, P.},
  title = {{Lost in the middle: How language models use long contexts}},
  date = {2023},
  eprint = {2307.03172},
  eprinttype = {arxiv}
}

Download · JSON with CSL-JSON · the whole bibliography