Related papers: DAL: Dual Adversarial Learning for Dialogue Genera…

Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly…

DNN-based language models excel across various NLP tasks but remain highly vulnerable to textual adversarial attacks. While adversarial text generation is crucial for NLP security, explainability, evaluation, and data augmentation, related…

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

We introduce adversarial learning methods for data-driven generative modeling of the dynamics of $n^{th}$-order stochastic systems. Our approach builds on Generative Adversarial Networks (GANs) with generative model classes based on stable…

In recent years, Generative Adversarial Networks (GANs) have become a hot topic among researchers and engineers that work with deep learning. It has been a ground-breaking technique which can generate new pieces of content of data in a…

Data sparsity is one of the key challenges associated with model development in Natural Language Understanding (NLU) for conversational agents. The challenge is made more complex by the demand for high quality annotated utterances commonly…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…

We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data…

Evaluating open-domain dialogue systems is challenging for reasons such as the one-to-many problem, i.e., many appropriate responses other than just the golden response. As of now, automatic evaluation methods need better consistency with…

How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time,…

In offline RL, constraining the learned policy to remain close to the data is essential to prevent the policy from outputting out-of-distribution (OOD) actions with erroneously overestimated values. In principle, generative adversarial…

We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog. In contrast with earlier models such as DialoGPT, GODEL leverages a new phase of grounded pre-training designed to better support…

Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model…

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by…

Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose an adversarial…

We present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and…

Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of…