DUnE: Dataset for Unified Editing

Afra Akyürek, Eric Pan, Garry Kuwanto, Derry Wijaya


Abstract
Even the most advanced language models remain susceptible to errors necessitating to modify these models without initiating a comprehensive retraining process. Model editing refers to the modification of a model’s knowledge or representations in a manner that produces the desired outcomes. Prior research primarily centered around editing factual data e.g. “Messi plays for Inter Miami” confining the definition of an edit to a knowledge triplet i.e. (subject, object, relation). However, as the applications of language models expand, so do the diverse ways in which we wish to edit and refine their outputs. In this study, we broaden the scope of the editing problem to include an array of editing cases such as debiasing and rectifying reasoning errors and define an edit as any natural language expression that solicits a change in the model’s outputs. We are introducing DUnE, an editing benchmark where edits are natural language sentences and propose that DUnE presents a challenging yet relevant task. To substantiate this claim, we conduct an extensive series of experiments testing various editing approaches to address DUnE, demonstrating their respective strengths and weaknesses. We argue that retrieval-augmented language modeling can outperform specialized editing techniques and neither set of approaches has fully solved the generalized editing problem covered by our benchmark.
Anthology ID:
2023.emnlp-main.114
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1847–1861
Language:
URL:
https://aclanthology.org/2023.emnlp-main.114
DOI:
10.18653/v1/2023.emnlp-main.114
Bibkey:
Cite (ACL):
Afra Akyürek, Eric Pan, Garry Kuwanto, and Derry Wijaya. 2023. DUnE: Dataset for Unified Editing. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1847–1861, Singapore. Association for Computational Linguistics.
Cite (Informal):
DUnE: Dataset for Unified Editing (Akyürek et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.114.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.114.mp4