Record
- Authors
- Berglund, L.; Tong, M.; Kaufmann, M.; Balesni, M.; Stickland, A. C.; Korbak, T.; Evans, O.
- Year
- 2024
- Title
- The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
- Published in
- Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024)
- Type
- Conference paper
- DOI
- 10.48550/arxiv.2309.12288
- arXiv
- arXiv:2309.12288
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4386977995 · DOI 10.48550/arxiv.2309.12288 · arXiv:2309.12288 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
berglund-2024-reversal-curse-llms-trained-is-b
Cited on
- Studying Large Language Model Generalization with Influence Functions read status: not stated
As cited
The pages cite this work in one form.
-
Berglund, L., Tong, M., Kaufmann, M., Balesni, M., Stickland, A. C., Korbak, T., and Evans, O. (2024). The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A". In Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024). arXiv:2309.12288 (version 4 read).
BibLaTeX
@inproceedings{berglund-2024-reversal-curse-llms-trained-is-b,
author = {Berglund, L. and Tong, M. and Kaufmann, M. and Balesni, M. and Stickland, A. C. and Korbak, T. and Evans, O.},
title = {{The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"}},
booktitle = {Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024)},
date = {2024},
doi = {10.48550/arxiv.2309.12288},
eprint = {2309.12288},
eprinttype = {arxiv}
}