English
Related papers

Related papers: Improving Question Answering Model Robustness with…

200 papers

We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating model robustness,…

Machine Learning · Computer Science 2021-11-02 Maor Ivgi , Jonathan Berant

Recent years have witnessed impressive advances in challenging multi-hop QA tasks. However, these QA models may fail when faced with some disturbance in the input text and their interpretability for conducting multi-hop reasoning remains…

Computation and Language · Computer Science 2021-12-20 Jiayu Ding , Siyuan Wang , Qin Chen , Zhongyu Wei

Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically…

Computation and Language · Computer Science 2022-10-21 Lei Xu , Alfredo Cuesta-Infante , Laure Berti-Equille , Kalyan Veeramachaneni

Reinforcement learning has been shown to improve the performance of large language models. However, traditional approaches like RLHF or RLAIF treat the problem as single-step. As focus shifts toward more complex reasoning and agentic tasks,…

Artificial Intelligence · Computer Science 2025-04-29 Anna Goldie , Azalia Mirhoseini , Hao Zhou , Irene Cai , Christopher D. Manning

We present a human-and-model-in-the-loop process for dynamically generating datasets and training better performing and more robust hate detection models. We provide a new dataset of ~40,000 entries, generated and labelled by trained…

Computation and Language · Computer Science 2021-06-04 Bertie Vidgen , Tristan Thrush , Zeerak Waseem , Douwe Kiela

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Omid Poursaeed , Tianxing Jiang , Harry Yang , Serge Belongie , SerNam Lim

Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a…

Machine Learning · Computer Science 2021-06-28 Divyam Madaan , Jinwoo Shin , Sung Ju Hwang

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Machine Learning · Computer Science 2020-08-13 Alex Serban , Erik Poll , Joost Visser

Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to…

Computation and Language · Computer Science 2023-07-25 Neel Bhandari , Pin-Yu Chen

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

Question generation has recently gained a lot of research interest, especially with the advent of large language models. In and of itself, question generation can be considered 'AI-hard', as there is a lack of unanimously agreed sense of…

Information Retrieval · Computer Science 2022-10-19 Sreehari Sankar , Zhihang Dong

Adversarial data augmentation has shown promise for training robust deep neural networks against unforeseen data shifts or corruptions. However, it is difficult to define heuristics to generate effective fictitious target distributions…

Machine Learning · Computer Science 2020-12-21 Long Zhao , Ting Liu , Xi Peng , Dimitris Metaxas

Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…

Machine Learning · Computer Science 2020-11-06 Calvin Luo , Hossein Mobahi , Samy Bengio

Hate speech detection models are only as good as the data they are trained on. Datasets sourced from social media suffer from systematic gaps and biases, leading to unreliable models with simplistic decision boundaries. Adversarial…

Computation and Language · Computer Science 2024-03-29 Janis Goldzycher , Paul Röttger , Gerold Schneider

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as…

Computation and Language · Computer Science 2019-04-05 Sudha Rao , Hal Daumé

Question Answering (QA) systems face challenges in handling complex questions that require multi-domain knowledge synthesis. The naive RAG models, although effective in information retrieval, struggle with complex questions that require…

Computation and Language · Computer Science 2024-10-24 Ziyang Chen , Xiaobin Wang , Yong Jiang , Jinzhi Liao , Pengjun Xie , Fei Huang , Xiang Zhao

Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Andras Rozsa , Manuel Günther , Terrance E. Boult

The detection of computer-generated text is an area of rapidly increasing significance as nascent generative models allow for efficient creation of compelling human-like text, which may be abused for the purposes of spam, disinformation,…

Computation and Language · Computer Science 2022-10-05 Evan Crothers , Nathalie Japkowicz , Herna Viktor , Paula Branco