Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F24%3A00135399" target="_blank" >RIV/00216224:14330/24:00135399 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2024.eacl-long.133.pdf" target="_blank" >https://aclanthology.org/2024.eacl-long.133.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

9798891760882

ISSN

—

e-ISSN

—

Number of pages

15

Pages from-to

2179-2193

Publisher name

Association for Computational Linguistics

Place of publication

St. Julian's, Malta

Event location

St. Julian's, Malta

Event date

Mar 17, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001356732602016