Related papers: A Distributional Approach to Controlled Text Gener…

This paper introduces distribution-based prediction, a novel approach to using Large Language Models (LLMs) as predictive tools by interpreting output token probabilities as distributions representing the models' learned representation of…

Although auto-regressive models excel in natural language processing, they often struggle to generate diverse text and provide limited controllability. Non-auto-regressive methods could be an alternative but often produce degenerate outputs…

Continuous-time generative models have achieved remarkable success in image restoration and synthesis. However, controlling the composition of multiple pre-trained models remains an open challenge. Current approaches largely treat…

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to…

The dominant language modeling paradigm handles text as a sequence of discrete tokens. While that approach can capture the latent structure of the text, it is inherently constrained to sequential dynamics for text generation. We propose a…

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 Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt…

Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs that adhere to logical constraints. Sampling from a…

Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To…

Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt. In this work, we attempt to systematically understand the probability distributions that LMs can produce, showing…

Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional form of the target distribution and the algorithm used to…

Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text…

The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a…

As a prominent challenge in addressing real-world issues within a dynamic environment, label shift, which refers to the learning setting where the source (training) and target (testing) label distributions do not match, has recently…

Prior work in style-controlled text generation has focused on tasks such as emulating the style of prolific literary authors, producing formal or informal text, and mitigating toxicity of generated text. Plentiful demonstrations of these…

This paper explores the application of Stochastic Differential Equations (SDE) to interpret the text generation process of Large Language Models (LLMs) such as GPT-4. Text generation in LLMs is modeled as a stochastic process where each…

Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses. Moreover, the expertise needed…

Diffusion models have attained prominence for their ability to synthesize a probability distribution for a given dataset via a diffusion process, enabling the generation of new data points with high fidelity. However, diffusion processes…

Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent. However,…