Related papers: FORTAP: Using Formulas for Numerical-Reasoning-Awa…
Data tables play a central role in scientific papers. However, their meaning is often co-constructed with surrounding text through narrative interplay, making comprehension cognitively demanding for readers. In this work, we explore how…
Large pre-trained language models (LMs) are known to encode substantial amounts of linguistic information. However, high-level reasoning skills, such as numerical reasoning, are difficult to learn from a language-modeling objective only.…
This paper proposes a novel architecture to generate multi-hop answers to open domain questions that require information from texts and tables, using the Open Table-and-Text Question Answering dataset for validation and training. One of the…
Spreadsheet formula prediction has been an important program synthesis problem with many real-world applications. Previous works typically utilize input-output examples as the specification for spreadsheet formula synthesis, where each…
Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence. We present SCITAB, a challenging evaluation dataset consisting of 1.2K…
Research on formulae production in spreadsheets has established the practice as high risk yet unrecognised as such by industry. There are numerous software applications that are designed to audit formulae and find errors. However these are…
Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer…
We study a new problem setting of question answering (QA), referred to as DocTabQA. Within this setting, given a long document, the goal is to respond to questions by organizing the answers into structured tables derived directly from the…
Table reasoning (TR) requires structured reasoning over semi-structured tabular data and remains challenging, particularly for small language models (SLMs, e.g., LLaMA-8B) due to their limited capacity compared to large LMs (LLMs, e.g.,…
Storing tabular data to balance storage and query efficiency is a long-standing research question in the database community. In this work, we argue and show that a novel DeepMapping abstraction, which relies on the impressive memorization…
Tabular datasets are widely used in scientific disciplines such as biology. While these disciplines have already adopted AI methods to enhance their findings and analysis, they mainly use tree-based methods due to their interpretability. At…
In an era where symbolic mathematical equations are indispensable for modeling complex natural phenomena, scientific inquiry often involves collecting observations and translating them into mathematical expressions. Recently, deep learning…
Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by pretraining on large volumes of synthetic data. The prior knowledge obtained via pretraining…
We introduce TabRepo, a new dataset of tabular model evaluations and predictions. TabRepo contains the predictions and metrics of 1310 models evaluated on 200 classification and regression datasets. We illustrate the benefit of our dataset…
Tables form a central component in both exploratory data analysis and formal reporting procedures across many industries. These tables are often complex in their conceptual structure and in the computations that generate their individual…
Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study these challenges through the problem of tabular natural…
Table extraction from document images is a challenging AI problem, and labelled data for many content domains is difficult to come by. Existing table extraction datasets often focus on scientific tables due to the vast amount of academic…
Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…
Table understanding is key to addressing challenging downstream tasks such as table-based question answering and fact verification. Recent works have focused on leveraging Chain-of-Thought and question decomposition to solve complex…
Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task,…