Related papers: Boosting Naturalness of Language in Task-oriented …

Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…

Most of the existing spoken language understanding systems can perform only semantic frame parsing based on a single-round user query. They cannot take users' feedback to update/add/remove slot values through multiround interactions with…

Adversarial training, a method for learning robust deep neural networks, constructs adversarial examples during training. However, recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence…

Simulation-based training (SBT) is gaining popularity as a low-cost and convenient training technique in a vast range of applications. However, for a SBT platform to be fully utilized as an effective training tool, it is essential that…

Recently, unsupervised pre-training is gaining increasing popularity in the realm of computational linguistics, thanks to its surprising success in advancing natural language understanding (NLU) and the potential to effectively exploit…

This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models. It involves applying gradient-based perturbation on the sentence…

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial…

Open domain neural dialogue models, despite their successes, are known to produce responses that lack relevance, diversity, and in many cases coherence. These shortcomings stem from the limited ability of common training objectives to…

Fine-tuning large language models (LLMs) for alignment typically relies on supervised fine-tuning or reinforcement learning from human feedback, both limited by the cost and scarcity of high-quality annotations. Recent self-play and…

Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks. In order for such models to truly be useful, they must be capable of correctly generating utterances for…

Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a class of input-agnostic attacks where a common trigger…

In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…

Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF…

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused…

Generative artificial intelligence (AI) has the potential to scale up personalized tutoring through large language models (LLMs). Recent AI tutors are adapted for the tutoring task by training or prompting LLMs to follow effective…

While deep learning in the form of recurrent neural networks (RNNs) has caused a significant improvement in neural language modeling, the fact that they are extremely prone to overfitting is still a mainly unresolved issue. In this paper we…

Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses. In this paper, we propose to explore potential responses by counterfactual reasoning. Given an observed response, the…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP). However, in contrast to the computer vision domain where…

Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper,…