EvEntS ReaLM: Event Reasoning of Entity States via Language Models

Evangelia Spiliopoulou, Artidoro Pagnoni, Yonatan Bisk, Eduard Hovy


Abstract
This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to procedural knowledge about how objects interact, yet our benchmarking shows they fail to reason about the world. Conversely, we also demonstrate that existing approaches often misrepresent the surprising abilities of LLMs via improper task encodings and that proper model prompting can dramatically improve performance of reported baseline results across multiple tasks. In particular, our results indicate that our prompting technique is especially useful for unseen attributes (out-of-domain) or when only limited data is available.
Anthology ID:
2022.emnlp-main.129
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1982–1997
Language:
URL:
https://aclanthology.org/2022.emnlp-main.129
DOI:
Bibkey:
Cite (ACL):
Evangelia Spiliopoulou, Artidoro Pagnoni, Yonatan Bisk, and Eduard Hovy. 2022. EvEntS ReaLM: Event Reasoning of Entity States via Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1982–1997, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
EvEntS ReaLM: Event Reasoning of Entity States via Language Models (Spiliopoulou et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-ingestion/2022.emnlp-main.129.pdf