Promptly Predicting Structures: The Return of Inference

Maitrey Mehta, Valentina Pyatkin, Vivek Srikumar


Abstract
Prompt-based methods have been used extensively across NLP to build zero- and few-shot label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of multiple labels which constrain each other. Annotating data for such tasks can be cumbersome. Can the promise of the prompt-based paradigm be extended to such structured outputs? In this paper, we present a framework for constructing zero- and few-shot linguistic structure predictors. Our key insight is that we can use structural constraints—and combinatorial inference derived from them—to filter out inconsistent structures predicted by large language models. We instantiated this framework on two structured prediction tasks, and five datasets. Across all cases, our results show that enforcing consistency not only constructs structurally valid outputs, but also improves performance over the unconstrained variants.
Anthology ID:
2024.naacl-long.7
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
112–130
Language:
URL:
https://aclanthology.org/2024.naacl-long.7
DOI:
Bibkey:
Cite (ACL):
Maitrey Mehta, Valentina Pyatkin, and Vivek Srikumar. 2024. Promptly Predicting Structures: The Return of Inference. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 112–130, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Promptly Predicting Structures: The Return of Inference (Mehta et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.7.pdf
Copyright:
 2024.naacl-long.7.copyright.pdf