![Thumbnail](/bitstream/handle/20.500.11850/669685/2023.acl-long.783.pdf.jpg?sequence=5&isAllowed=y)
Open access
Date
2023-07Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
Various design settings for in-context learning (ICL), such as the choice and order of the in-context examples, can bias the model's predictions. While many studies discuss these design choices, there have been few systematic investigations into categorizing them and mitigating their impact. In this work, we define a typology for three types of label biases in ICL for text classification: vanilla-label bias, contextlabel bias, and domain-label bias (which we conceptualize and detect for the first time). Our analysis demonstrates that prior label bias calibration methods fall short of addressing all three types of biases. Specifically, domain-label bias restricts LLMs to random-level performance on many tasks regardless of the choice of in-context examples. To mitigate the effect of these biases, we propose a simple bias calibration method that estimates a language model's label bias using random indomain words from the task corpus. After controlling for this estimated bias when making predictions, our novel domain-context calibration significantly improves the ICL performance of GPT-J and GPT-3 on a wide range of tasks. The gain is substantial on tasks with large domain-label bias (up to 37% in Macro-F1). Furthermore, our results generalize to models with different scales, pretraining methods, and manually-designed task instructions, showing the prevalence of label biases in ICL. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000669685Publication status
publishedExternal links
Book title
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)Pages / Article No.
Publisher
Association for Computational LinguisticsEvent
Related publications and datasets
Is supplemented by: https://aclanthology.org/2023.acl-long.783.mp4
More
Show all metadata
ETH Bibliography
yes
Altmetrics