相关论文: NL2Formula: Generating Spreadsheet Formulas from N…

Large language models (LLMs) enable system builders today to create competent NLP systems through prompting, where they only need to describe the task in natural language and provide a few examples. However, in other ways, LLMs are a step…

Neural natural language generation (NLG) models have recently shown remarkable progress in fluency and coherence. However, existing studies on neural NLG are primarily focused on surface-level realizations with limited emphasis on logical…

Recently, Large Language Models (LLMs) have demonstrated great potential in natural language-driven molecule discovery. However, existing datasets and benchmarks for molecule-text alignment are predominantly built on one-to-one mappings,…

Selecting a subset of cells is a common task in data engineering, for example, to remove errors or select only specific parts of a table. Multiple approaches to express this selection exist. One option is numeric indexing, commonly found in…

Amongst the large number of write-and-throw-away spreadsheets developed for one-time use there is a rather neglected proportion of spreadsheets that are huge, periodically used, and submitted to regular update-cycles like any conventionally…

The automated generation of research workflows is essential for improving the reproducibility of research and accelerating the paradigm of "AI for Science". However, existing methods typically extract merely fragmented procedural components…

Formatting is an important property in tables for visualization, presentation, and analysis. Spreadsheet software allows users to automatically format their tables by writing data-dependent conditional formatting (CF) rules. Writing such…

We investigate the expressive power of spreadsheets. We consider spreadsheets which contain only formulas, and assume that they are small templates, which can be filled to a larger area of the grid to process input data of variable size.…

This paper introduces the human-curated PandasPlotBench dataset, designed to evaluate language models' effectiveness as assistants in visual data exploration. Our benchmark focuses on generating code for visualizing tabular data - such as a…

Efficient querying and analysis of large tabular datasets remain significant challenges, especially for users without expertise in programming languages like SQL. Text-to-SQL approaches have shown promising performance on benchmark data;…

Context: Tables are ubiquitous formats for data. Therefore, techniques for writing correct programs over tables, and debugging incorrect ones, are vital. Our specific focus in this paper is on rich types that articulate the properties of…

Confidentiality hinders the publication of authentic, labeled datasets of personal and enterprise data, although they could be useful for evaluating knowledge graph construction approaches in industrial scenarios. Therefore, our plan is to…

We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse…

Tables are often created with hierarchies, but existing works on table reasoning mainly focus on flat tables and neglect hierarchical tables. Hierarchical tables challenge existing methods by hierarchical indexing, as well as implicit…

Robust evaluation in the presence of linguistic variation is key to understanding the generalization capabilities of Natural Language to SQL (NL2SQL) models, yet existing benchmarks rarely address this factor in a systematic or controlled…

In this paper, we present a multi-lingual sentence encoder that can be used in search engines as a query and document encoder. This embedding enables a semantic similarity score between queries and documents that can be an important feature…

When spreadsheets are filled freely by knowledge workers, they can contain rather unstructured content. For humans and especially machines it becomes difficult to interpret such data properly. Therefore, spreadsheets are often converted to…

Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale,…

Writing software exploits is an important practice for offensive security analysts to investigate and prevent attacks. In particular, shellcodes are especially time-consuming and a technical challenge, as they are written in assembly…

Charts are commonly used for exploring data and communicating insights. Generating natural language summaries from charts can be very helpful for people in inferring key insights that would otherwise require a lot of cognitive and…