相关论文: Learn What NOT to Learn: Towards Generative Safety…

Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the…

In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the…

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets (GAN) that…

Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render…

We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss function used…

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process.…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable…

Existing NTMs with contrastive learning suffer from the sample bias problem owing to the word frequency-based sampling strategy, which may result in false negative samples with similar semantics to the prototypes. In this paper, we aim to…

The recent advances in diffusion models (DMs) have revolutionized the generation of realistic and complex images. However, these models also introduce potential safety hazards, such as producing harmful content and infringing data…

Generating a Chain of Thought (CoT) has been shown to consistently improve large language model (LLM) performance on a wide range of NLP tasks. However, prior work has mainly focused on logical reasoning tasks (e.g. arithmetic, commonsense…

It is important for robots to be able to decide whether they can go through a space or not, as they navigate through a dynamic environment. This capability can help them avoid injury or serious damage, e.g., as a result of running into…

The rapid development of artificial intelligence (AI) technology has enabled large-scale AI applications to land in the market and practice. However, while AI technology has brought many conveniences to people in the productization process,…