Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2365639,
author = {Mikula, Lukáš and Štefánik, Michal and Petrovič, Marek and Sojka, Petr},
address = {St. Julian's, Malta},
booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
editor = {Yvette Graham, Matthew Purver},
keywords = {LLM; Large Language Models; bias; Question Answering;},
howpublished = {tištěná verze "print"},
language = {eng},
location = {St. Julian's, Malta},
isbn = {979-8-89176-088-2},
pages = {2179-2193},
publisher = {Association for Computational Linguistics},
title = {Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models},
url = {https://openreview.net/forum?id=8GkrxUgjg0},
year = {2024}
}
TY - JOUR
ID - 2365639
AU - Mikula, Lukáš - Štefánik, Michal - Petrovič, Marek - Sojka, Petr
PY - 2024
TI - Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models
PB - Association for Computational Linguistics
CY - St. Julian's, Malta
SN - 9798891760882
KW - LLM
KW - Large Language Models
KW - bias
KW - Question Answering;
UR - https://openreview.net/forum?id=8GkrxUgjg0
N2 - While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model robustness by evaluating their models on out-of-distribution (OOD) datasets of the same task, but these datasets might share the bias of the training dataset. We propose a simple method for measuring a scale of models' reliance on any identified spurious feature and assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA). We find that the reported OOD gains of debiasing methods can not be explained by mitigated reliance on biased features, suggesting that biases are shared among QA datasets. We further evidence this by measuring that performance of OOD models depends on bias features comparably to the ID model, motivating future work to refine the reports of LLMs' robustness to a level of known spurious features.
ER -
MIKULA, Lukáš, Michal ŠTEFÁNIK, Marek PETROVIČ and Petr SOJKA. Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models. In Yvette Graham, Matthew Purver. \textit{Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)}. St. Julian's, Malta: Association for Computational Linguistics, 2024, p.~2179-2193. ISBN~979-8-89176-088-2.
|
