Related papers: Improving Maximum Likelihood Training for Text Gen…

Generative Artificial Intelligence (GenAI) models, with their powerful feature learning capabilities, have been applied in many fields. In mobile wireless communications, GenAI can dynamically optimize the network to enhance the user…

Controlled text generation tasks such as unsupervised text style transfer have increasingly adopted the use of Reinforcement Learning (RL). A major challenge in applying RL to such tasks is the sparse reward, which is available only after…

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

Language models are generally trained on data spanning a wide range of topics (e.g., news, reviews, fiction), but they might be applied to an a priori unknown target distribution (e.g., restaurant reviews). In this paper, we first show that…

Every student in statistics or data science learns early on that when the sample size largely exceeds the number of variables, fitting a logistic model produces estimates that are approximately unbiased. Every student also learns that there…

As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes human-authored text. Since online data is the primary resource…

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Misclassification of binary responses, if ignored, may severely bias the maximum likelihood estimators (MLE) of regression parameters. For such data, a binary regression model incorporating misclassification probabilities is extensively…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Language generation based on maximum likelihood estimation (MLE) has become the fundamental approach for text generation. Maximum likelihood estimation is typically performed by minimizing the log-likelihood loss, also known as the…

In this work, we explore the theoretical properties of conditional deep generative models under the statistical framework of distribution regression where the response variable lies in a high-dimensional ambient space but concentrates…

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

Large language models (LLMs) have reached human-like proficiency in generating diverse textual content, underscoring the necessity for effective fake text detection to avoid potential risks such as fake news in social media. Previous…

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…

Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation. A common practice to improve generation diversity is to sample multiple outputs from the model. However, there lacks a simple…

Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the base autoregressive…

Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the…

Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. Recently, methods based on meta-learning have shown promising results for few-shot domain…

In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models. Our method constructs an energy function on the latent variable space that yields an energy function on…

Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate…