Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models
Pre-trained language models have achieved human-level performance on many Machine Reading Comprehension (MRC) tasks, but it remains unclear whether these models truly understand language or answer questions by exploiting statistical biases in datasets. Here, we demonstrate a simple yet effective method to attack MRC models and reveal the statistical biases in these models. We apply the method to the RACE dataset, for which the answer to each MRC question is selected from 4 options. It is found that several pre-trained language models, including BERT, ALBERT, and RoBERTa, show consistent preference to some options, even when these options are irrelevant to the question. When interfered by these irrelevant options, the performance of MRC models can be reduced from human-level performance to the chance-level performance. Human readers, however, are not clearly affected by these irrelevant options. Finally, we propose an augmented training method that can greatly reduce models' statistical biases.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine Reading ComprehensionReading ComprehensionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability
Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into one model that retains performance across …
Adversarial RobustnessMulti-Task LearningAdversarial AttackHow Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness
Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a represent…
Frequency maps reveal the correlation between Adversarial Attacks and Implicit Bias
Despite their impressive performance in classification tasks, neural networks are known to be vulnerable to adversarial attacks, subtle perturbations of the input data designed to deceive the model. In this work, we inve…
Image ClassificationDetecting Malicious Accounts showing Adversarial Behavior in Permissionless Blockchains
Different types of malicious activities have been flagged in multiple permissionless blockchains such as bitcoin, Ethereum etc. While some malicious activities exploit vulnerabilities in the infrastructure of the blockch…
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
It is widely known that state-of-the-art machine learning models, including vision and language models, can be seriously compromised by adversarial perturbations. It is therefore increasingly relevant to develop capabili…
Adversarial AttackBayesian Optimization