Related papers: Facts-and-Feelings: Capturing both Objectivity and…

Translating users' natural language queries (NL) into SQL queries (i.e., Text-to-SQL, a.k.a. NL2SQL) can significantly reduce barriers to accessing relational databases and support various commercial applications. The performance of…

Neural models have recently been used in text summarization including headline generation. The model can be trained using a set of document-headline pairs. However, the model does not explicitly consider topical similarities and differences…

In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs. A central challenge of this task lies in accurately…

We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Previous efforts to construct such datasets relied on crowd-sourcing, but the emergence of…

The task of table summarization involves generating text that both succinctly and accurately represents the table or a specific set of highlighted cells within a table. While significant progress has been made in table to text generation…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their enormous parameter size and extremely high requirements for compute power pose challenges for…

Humans continuously make new discoveries, and understanding temporal sequence of events leading to these breakthroughs is essential for advancing science and society. This ability to reason over time allows us to identify future steps and…

Table Structure Recognition (TSR) requires the logical reasoning ability of large language models (LLMs) to handle complex table layouts, but current datasets are limited in scale and quality, hindering effective use of this reasoning…

With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, but inconsistent datasets, evaluation metrics, and assessment strategies obscure…

Advances in text-to-speech (TTS) technology have significantly improved the quality of generated speech, closely matching the timbre and intonation of the target speaker. However, due to the inherent complexity of human emotional…

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However, the generated data…

In modern industry systems like multi-turn chat agents, Text-to-SQL technology bridges natural language (NL) questions and database (DB) querying. The conversion of tabular DB results into NL representations (NLRs) enables the chat-based…

Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with…

Humans often rely on subjective natural language to direct language models (LLMs); for example, users might instruct the LLM to write an enthusiastic blogpost, while developers might train models to be helpful and harmless using LLM-based…

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its…

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…

When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we address this challenge by utilizing large language models (LLMs)…

Large Language Models (LLMs) possess an extraordinary capability to produce text that is not only coherent and contextually relevant but also strikingly similar to human writing. They adapt to various styles and genres, producing content…

In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain…