Ellipsis-Dependent Reasoning: a New Challenge for Large Language Models

Daniel Hardt


Abstract
We propose a novel challenge for large language models: ellipsis-dependent reasoning. We define several structures of paired examples, where an ellipsis example is matched to its non-ellipsis counterpart, and a question is posed which requires resolution of the ellipsis. Test results show that the best models perform well on non-elliptical examples but struggle with all but the simplest ellipsis structures.
Anthology ID:
2023.acl-short.4
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
39–47
Language:
URL:
https://aclanthology.org/2023.acl-short.4
DOI:
10.18653/v1/2023.acl-short.4
Bibkey:
Cite (ACL):
Daniel Hardt. 2023. Ellipsis-Dependent Reasoning: a New Challenge for Large Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 39–47, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Ellipsis-Dependent Reasoning: a New Challenge for Large Language Models (Hardt, ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-short.4.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-short.4.mp4