Nothing Special   »   [go: up one dir, main page]

Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations

Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, Taeuk Kim


Abstract
Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive.Intuitively, ground-truth labels should have as much impact in in-context learning (ICL) as supervised learning, but recent work reported that the input-label correspondence is significantly less important than previously thought.Intrigued by this counter-intuitive observation, we re-examine the importance of ground-truth labels in in-context learning.With the introduction of two novel metrics, namely Label-Correctness Sensitivity and Ground-truth Label Effect Ratio (GLER), we were able to conduct quantifiable analysis on the impact of ground-truth label demonstrations.Through extensive analyses, we find that the correct input-label mappings can have varying impacts on the downstream in-context learning performances, depending on the experimental configuration.Through additional studies, we identify key components, such as the verbosity of prompt templates and the language model size, as the controlling factor to achieve more noise-resilient ICL.
Anthology ID:
2022.emnlp-main.155
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2422–2437
Language:
URL:
https://aclanthology.org/2022.emnlp-main.155
DOI:
10.18653/v1/2022.emnlp-main.155
Bibkey:
Cite (ACL):
Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, and Taeuk Kim. 2022. Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2422–2437, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations (Yoo et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.155.pdf