Related papers: Confidence Regularized Masked Language Modeling us…

Consistency regularization is a commonly used practice to encourage the model to generate consistent representation from distorted input features and improve model generalization. It shows significant improvement on various speech…

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs.…

The uniform information density (UID) hypothesis, which posits that speakers behaving optimally tend to distribute information uniformly across a linguistic signal, has gained traction in psycholinguistics as an explanation for certain…

The ability to extrapolate from short problem instances to longer ones is an important form of out-of-distribution generalization in reasoning tasks, and is crucial when learning from datasets where longer problem instances are rare. These…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be…

Vision Language Models (VLMs) can be trained more efficiently if training sets can be reduced in size. Recent work has shown the benefits of masking text during VLM training using a variety of strategies (truncation, random masking, block…

Iterative pruning is one of the most effective compression methods for pre-trained language models. We discovered that finding the optimal pruning decision is an equality-constrained 0-1 Integer Linear Programming problem. The solution to…

Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident…

Retriever-reader models achieve competitive performance across many different NLP tasks such as open question answering and dialogue conversations. In this work, we notice these models easily overfit the top-rank retrieval passages and…

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their…

Lip reading, the process of interpreting silent speech from visual lip movements, has gained rising attention for its wide range of realistic applications. Deep learning approaches greatly improve current lip reading systems. However, lip…

In safety-critical applications, language models should be able to characterize their uncertainty with meaningful probabilities. Many uncertainty quantification approaches require supervised data; however, finding suitable unseen…

Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which…

Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic,…

Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network…

Estimating the log-likelihood of a given sentence under an autoregressive language model is straightforward: one can simply apply the chain rule and sum the log-likelihood values for each successive token. However, for masked language…

Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In…

Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for downstream task…