Related papers: Residual Energy-Based Models for Text Generation

Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the…

Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive…

While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic template-based systems provide strong guarantees of faithfulness…

Large language models (LLMs) are a basic infrastructure for modern natural language processing. Many commercial and open-source LLMs exist for English, e.g., ChatGPT, Llama, Falcon, and Mistral. As these models are trained on mostly English…

We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from…

Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…

Energy-based models (EBMs) offer a flexible framework for parameterizing probability distributions using neural networks. However, learning EBMs by exact maximum likelihood estimation (MLE) is generally intractable, due to the need to…

Generative Adversarial Networks (GANs) have shown great promise recently in image generation. Training GANs for language generation has proven to be more difficult, because of the non-differentiable nature of generating text with recurrent…

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…

Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

The Energy-Based Model (EBM) framework is a very general approach to generative modeling that tries to learn and exploit probability distributions only defined though unnormalized scores. It has risen in popularity recently thanks to the…

Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perform discrimination. Despite great advances in model…

Deep neural networks (DNNs) are easily fooled by adversarial perturbations that are imperceptible to humans. Adversarial training, a process where adversarial examples are added to the training set, is the current state-of-the-art defense…

Large-scale Causal Language Models (CLMs), e.g., GPT3 and ChatGPT, have brought great success in text generation. However, it is still an open challenge to control the generation process of CLM while balancing flexibility, control…

Neural networks have excelled at many NLP tasks, but there remain open questions about the performance of pretrained distributed word representations and their interaction with weight initialization and other hyperparameters. We address…

We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for…

In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…

Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling…

Large Language Models (LLMs) have been found to memorize and recite some of the textual sequences from their training set verbatim, raising broad concerns about privacy and copyright issues when using LLMs. This Textual Sequence…