Label-Efficient Model Selection for Text Generation

Shir Ashury Tahan, Ariel Gera, Benjamin Sznajder, Leshem Choshen, Liat Ein-Dor, Eyal Shnarch


Abstract
Model selection for a given target task can be costly, as it may entail extensive annotation of the quality of outputs of different models. We introduce DiffUse, an efficient method to make an informed decision between candidate text generation models based on preference annotations. DiffUse reduces the required amount of annotations, thus saving valuable time and resources in performing evaluation.DiffUse intelligently selects instances by clustering embeddings that represent the semantic differences between model outputs. Thus, it is able to identify a subset of examples that are more informative for preference decisions. Our method is model-agnostic, and can be applied to any text generation model for selecting between models, prompts and configurations. Moreover, we propose a practical iterative approach for dynamically determining how many instances to annotate. In a series of experiments over hundreds of model pairs, we demonstrate that DiffUse can dramatically reduce the required number of annotations – by up to 75% – while maintaining high evaluation reliability.
Anthology ID:
2024.acl-long.456
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8384–8402
Language:
URL:
https://aclanthology.org/2024.acl-long.456
DOI:
10.18653/v1/2024.acl-long.456
Bibkey:
Cite (ACL):
Shir Ashury Tahan, Ariel Gera, Benjamin Sznajder, Leshem Choshen, Liat Ein-Dor, and Eyal Shnarch. 2024. Label-Efficient Model Selection for Text Generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8384–8402, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Label-Efficient Model Selection for Text Generation (Ashury Tahan et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.456.pdf