paper-with-me

Papers

Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models

2021-05-24 · ACL 2021 5 · Jieyu Lin, Jiajie Zou, Nai Ding

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.

📄 PDF Abstract BibTeX arXiv:2105.11136

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Reading ComprehensionReading Comprehension

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
LAMB LAMB is a a layerwise adaptive large batch optimization technique. It provides a strategy for adapting the learning rate in large batch settings. LAMB uses…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability

2025-09-28 · Ankit Gangwal, Aaryan Ajay Sharma arxiv

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 Attack

How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness

2026-01-20 · Giulio Rossolini arxiv

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

2023-05-24 · Lorenzo Basile, Nikos Karantzas, Alberto D'Onofrio, Luca Manzoni 외

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 Classification

Detecting Malicious Accounts showing Adversarial Behavior in Permissionless Blockchains

2021-01-28 · Rachit Agarwal, Tanmay Thapliyal, Sandeep K. Shukla

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

2024-02-04 · Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic 외

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