Related papers: QUIETT: Query-Independent Table Transformation for…
We explore using T5 (Raffel et al. (2019)) to directly translate natural language questions into SQL statements. General purpose natural language that interfaces to information stored within databases requires flexibly translating natural…
The exponential growth of AI in science necessitates efficient and scalable solutions for retrieving and preserving research information. Here, we present a tool for the development of a customized question-answer (QA) dataset, called…
Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer, rather than only the region containing the final response. Creating such…
This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources. The system adopts a RAG-based architecture, with a pipeline of evidence…
Existing datasets for tabular question answering typically focus exclusively on text within cells. However, real-world data is inherently multimodal, often blending images such as symbols, faces, icons, patterns, and charts with textual…
Multiple-choice questions (MCQs) are widely used to evaluate large language models (LLMs). However, LLMs remain vulnerable to the presence of plausible distractors. This often diverts attention toward irrelevant choices, resulting in…
Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…
Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they…
Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. The framework first plans the reasoning paths over…
Conversational question answering (QA) requires the ability to correctly interpret a question in the context of previous conversation turns. We address the conversational QA task by decomposing it into question rewriting and question…
The problem of verifying whether a textual hypothesis holds based on the given evidence, also known as fact verification, plays an important role in the study of natural language understanding and semantic representation. However, existing…
In-context learning (ICL) capabilities are foundational to the success of large language models (LLMs). Recently, context compression has attracted growing interest since it can largely reduce reasoning complexities and computation costs of…
A myriad of different Large Language Models (LLMs) face a common challenge in contextually analyzing table question-answering tasks. These challenges are engendered from (1) finite context windows for large tables, (2) multi-faceted…
In this paper, we describe a dataset and baseline result for a question answering that utilizes web tables. It contains commonly asked questions on the web and their corresponding answers found in tables on websites. Our dataset is novel in…
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…
Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static…
Improving the mathematical reasoning capabilities of Large Language Models (LLMs) is critical for advancing artificial intelligence. However, access to extensive, diverse, and high-quality reasoning datasets remains a significant challenge,…
Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…
We present a comprehensive study of chart visual question-answering(QA) task, to address the challenges faced in comprehending and extracting data from chart visualizations within documents. Despite efforts to tackle this problem using…
Vision-Language Model (VLM)-based image quality assessment (IQA) has been significantly advanced by incorporating Chain-of-Thought (CoT) reasoning. Recent work has refined image quality reasoning by applying reinforcement learning (RL) and…