Related papers: FreeLB: Enhanced Adversarial Training for Natural …
Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…
Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly uses an "attack"…
While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored.…
The field of adversarial robustness has attracted significant attention in machine learning. Contrary to the common approach of training models that are accurate in average case, it aims at training models that are accurate for worst case…
The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…
Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…
The release of large natural language inference (NLI) datasets like SNLI and MNLI have led to rapid development and improvement of completely neural systems for the task. Most recently, heavily pre-trained, Transformer-based models like…
Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…
This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word…
Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To address this, we propose a prompting framework that generates…
With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…
In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. We take inspiration from RelGAN, a model for text generation, and NMT-GAN, an adversarial machine translation model, to…
Offensive language detection is an ever-growing natural language processing (NLP) application. This growth is mainly because of the widespread usage of social networks, which becomes a mainstream channel for people to communicate, work, and…
Large pre-trained language representation models (LMs) have recently collected a huge number of successes in many NLP tasks. In 2018 BERT, and later its successors (e.g. RoBERTa), obtained state-of-the-art results in classical benchmark…
Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…
Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…
Although pre-trained language models (PLMs) have achieved state-of-the-art performance on various natural language processing (NLP) tasks, they are shown to be lacking in knowledge when dealing with knowledge driven tasks. Despite the many…
While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test data might not be…
Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While some recent works…
Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…