Related papers: Long and Diverse Text Generation with Planning-bas…

Automatic question generation from paragraphs is an important and challenging problem, particularly due to the long context from paragraphs. In this paper, we propose and study two hierarchical models for the task of question generation…

Manually generating catchy descriptions and names is labor intensive and a slow process for retailers. Although generative AI provides an automation solution in form of Vision to Language Models (VLM), the current VLMs are prone to factual…

The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and "hallucination". Due to the…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks (e.g., long-context understanding), and many benchmarks have been proposed. However, we observe that long text generation capabilities…

Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often leads to myopic…

The language generation and reasoning capabilities of large language models (LLMs) have enabled conversational systems with impressive performance in a variety of tasks, from code generation, to composing essays, to passing STEM and legal…

Token serves as the fundamental unit of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite its importance, existing approaches lack fine-grained…

Natural language generation (NLG) is a critical component in spoken dialogue system, which can be divided into two phases: (1) sentence planning: deciding the overall sentence structure, (2) surface realization: determining specific word…

Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on…

We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding--based approaches that consider each sequence separately, our proposed framework utilizes both sequences…

Safe and successful deployment of robots requires not only the ability to generate complex plans but also the capacity to frequently replan and correct execution errors. This paper addresses the challenge of long-horizon trajectory planning…

Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination. A promising solution to this issue is…

Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high…

The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as poor long-term planning, error accumulation, and…

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…

Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In…

Topic models are one of the compelling methods for discovering latent semantics in a document collection. However, it assumes that a document has sufficient co-occurrence information to be effective. However, in short texts, co-occurrence…

While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition…

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models…

The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. Recent research has…