Saved in:
Bibliographic Details
Main Authors: Wang, Yuefeng, Lee, ChangJae
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11581
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912829808836608
author Wang, Yuefeng
Lee, ChangJae
author_facet Wang, Yuefeng
Lee, ChangJae
contents Question-answering (QA) models have advanced significantly in machine reading comprehension but often exhibit biases that hinder their performance, particularly with complex queries in adversarial conditions. This study evaluates the ELECTRA-small model on the Stanford Question Answering Dataset (SQuAD) v1.1 and adversarial datasets AddSent and AddOneSent. By identifying errors related to lexical bias, numerical reasoning, and entity recognition, we develop a multi-domain debiasing framework incorporating knowledge distillation, debiasing techniques, and domain expansion. Our results demonstrate up to 2.6 percentage point improvements in Exact Match (EM) and F1 scores across all test sets, with gains in adversarial contexts. These findings highlight the potential of targeted bias mitigation strategies to enhance the robustness and reliability of natural language understanding systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11581
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing the QA Model through a Multi-domain Debiasing Framework
Wang, Yuefeng
Lee, ChangJae
Computation and Language
Artificial Intelligence
Question-answering (QA) models have advanced significantly in machine reading comprehension but often exhibit biases that hinder their performance, particularly with complex queries in adversarial conditions. This study evaluates the ELECTRA-small model on the Stanford Question Answering Dataset (SQuAD) v1.1 and adversarial datasets AddSent and AddOneSent. By identifying errors related to lexical bias, numerical reasoning, and entity recognition, we develop a multi-domain debiasing framework incorporating knowledge distillation, debiasing techniques, and domain expansion. Our results demonstrate up to 2.6 percentage point improvements in Exact Match (EM) and F1 scores across all test sets, with gains in adversarial contexts. These findings highlight the potential of targeted bias mitigation strategies to enhance the robustness and reliability of natural language understanding systems.
title Enhancing the QA Model through a Multi-domain Debiasing Framework
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.11581