相关论文: Facts-and-Feelings: Capturing both Objectivity and…

Text-to-SQL prompt strategies based on Large Language Models (LLMs) achieve remarkable performance on well-known benchmarks. However, when applied to real-world databases, their performance is significantly less than for these benchmarks,…

We propose a novel document generation process based on hierarchical latent tree models (HLTMs) learned from data. An HLTM has a layer of observed word variables at the bottom and multiple layers of latent variables on top. For each…

We investigate how large language models (LLMs) fail when tabular data in an otherwise canonical representation is subjected to semantic and structural distortions. Our findings reveal that LLMs lack an inherent ability to detect and…

Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

We introduce DataTales, a novel benchmark designed to assess the proficiency of language models in data narration, a task crucial for transforming complex tabular data into accessible narratives. Existing benchmarks often fall short in…

Large Language Models (LLMs) have shown promise in enabling natural language interfaces for structured data querying through text-to-SQL generation. However, their application in real-world Business Intelligence (BI) contexts remains…

Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from low coverage and poor faithfulness problems. To mitigate…

Existing data-to-text generation efforts mainly focus on generating a coherent text from non-linguistic input data, such as tables and attribute-value pairs, but overlook that different application scenarios may require texts of different…

In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record. We thus try to evaluate the generation faithfulness with two…

Generating captions for images is a task that has recently received considerable attention. In this work we focus on caption generation for abstract scenes, or object layouts where the only information provided is a set of objects and their…

Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation. However, a common class of real-world queries is implicitly predictive, requiring the…

Generating accurate SQL queries for user questions (text-to-SQL) has been a long-standing challenge since it requires a deep understanding of both the user's question and the corresponding database schema in order to retrieve the desired…

Data-driven storytelling is a powerful method for conveying insights by combining narrative techniques with visualizations and text. These stories integrate visual aids, such as highlighted bars and lines in charts, along with textual…

Query-focused table summarization requires generating natural language summaries of tabular data conditioned on a user query, enabling users to access insights beyond fact retrieval. Existing approaches face key limitations: table-to-text…

Although Seq2Seq models for table-to-text generation have achieved remarkable progress, modeling table representation in one dimension is inadequate. This is because (1) the table consists of multiple rows and columns, which means that…

Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To…

The ability of Large Language Models (LLMs) to generate structured outputs that follow arbitrary schemas is crucial to a wide range of downstream tasks that require diverse structured representations of results such as information…

Existing data-to-text generation datasets are mostly limited to English. To address this lack of data, we create Table-to-Text in African languages (TaTa), the first large multilingual table-to-text dataset with a focus on African…

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…