BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions

Arth Bohra, Govert Verkes, Artem Harutyunyan, Pascal Weinberger, Giovanni Campagna


Abstract
Text classification is a well-studied and versatile building block for many NLP applications. Yet, existing approaches require either large annotated corpora to train a model with or, when using large language models as a base, require carefully crafting the prompt as well as using a long context that can fit many examples. As a result, it is not possible for end-users to build classifiers for themselves. To address this issue, we propose a novel approach to few-shot text classification using an LLM. Rather than few-shot examples, the LLM is prompted with descriptions of the salient features of each class. These descriptions are coauthored by the user and the LLM interactively: while the user annotates each few-shot example, the LLM asks relevant questions that the user answers. Examples, questions, and answers are summarized to form the classification prompt. Our experiments show that our approach yields high accuracy classifiers, within 79% of the performance of models trained with significantly larger datasets while using only 1% of their training sets. Additionally, in a study with 30 participants, we show that end-users are able to build classifiers to suit their specific needs. The personalized classifiers show an average accuracy of 90%, which is 15% higher than the state-of-the-art approach.
Anthology ID:
2023.findings-emnlp.933
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13999–14015
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.933
DOI:
10.18653/v1/2023.findings-emnlp.933
Bibkey:
Cite (ACL):
Arth Bohra, Govert Verkes, Artem Harutyunyan, Pascal Weinberger, and Giovanni Campagna. 2023. BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13999–14015, Singapore. Association for Computational Linguistics.
Cite (Informal):
BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions (Bohra et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.933.pdf