Related papers: Mining Mathematical Documents for Question Answeri…

Pretrained Large Language Models (LLMs) have gained significant attention for addressing open-domain Question Answering (QA). While they exhibit high accuracy in answering questions related to common knowledge, LLMs encounter difficulties…

Question answering on free-form tables (a.k.a. TableQA) is a challenging task because of the flexible structure and complex schema of tables. Recent studies use Large Language Models (LLMs) for this task, exploiting their capability in…

Some Question Answering (QA) systems rely on knowledge bases (KBs) to provide accurate answers. Entity Linking (EL) plays a critical role in linking natural language mentions to KB entries. However, most existing EL methods are designed for…

While large language models (LMs) demonstrate remarkable performance, they encounter challenges in providing accurate responses when queried for information beyond their pre-trained memorization. Although augmenting them with relevant…

While the ecosystem of Lean and Mathlib has enjoyed celebrated success in formal mathematical reasoning with the help of large language models (LLMs), the absence of many folklore lemmas in Mathlib remains a persistent barrier that limits…

Progress in sentence simplification has been hindered by a lack of labeled parallel simplification data, particularly in languages other than English. We introduce MUSS, a Multilingual Unsupervised Sentence Simplification system that does…

Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable method to create…

Multiple web-scale Knowledge Bases, e.g., Freebase, YAGO, NELL, have been constructed using semi-supervised or unsupervised information extraction techniques and many of them, despite their large sizes, are continuously growing. Much…

Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includes encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also…

This paper presents a new framework for adding semantics into e-learning system. The proposed approach relies on two principles. The first principle is the automatic addition of semantic information when creating the mathematical contents.…

There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model…

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at…

Recently proposed long-form question answering (QA) systems, supported by large language models (LLMs), have shown promising capabilities. Yet, attributing and verifying their generated abstractive answers can be difficult, and…

It remains difficult to evaluate machine learning classifiers in the absence of a large, labeled dataset. While labeled data can be prohibitively expensive or impossible to obtain, unlabeled data is plentiful. Here, we introduce…

Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge coverage. Alternatively, prompting large language models…

The popularity of data science as a discipline and its importance in the emerging economy and industrial progress dictate that machine learning be democratized for the masses. This also means that the current practice of workforce training…

As Large Language Models (LLMs) advance, their potential for widespread societal impact grows simultaneously. Hence, rigorous LLM evaluations are both a technical necessity and social imperative. While numerous evaluation benchmarks have…

Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we…

Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation methods face…

Unstructured enterprise data such as reports, manuals and guidelines often contain tables. The traditional way of integrating data from these tables is through a two-step process of table detection/extraction and mapping the table layouts…