Related papers: Decomposition-Driven Multi-Table Retrieval and Rea…
Yes, repurposing multiple-choice question-answering (MCQA) models for document reranking is both feasible and valuable. This preliminary work is founded on mathematical parallels between MCQA decision-making and cross-encoder semantic…
Relational databases (RDBs) underpin the majority of global data management systems, where information is structured into multiple interdependent tables. To effectively use the knowledge within RDBs for predictive tasks, recent advances…
Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they often rely on a…
Table reasoning is a challenging task that requires understanding both natural language questions and structured tabular data. Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation,…
We introduce MemSum-DQA, an efficient system for document question answering (DQA) that leverages MemSum, a long document extractive summarizer. By prefixing each text block in the parsed document with the provided question and question…
Multimodal large language models (MLLMs) have demonstrated great performance on visual question answering (VQA). When it comes to knowledge-based Visual Question Answering (KB-VQA), MLLMs may lack the specialized domain knowledge needed to…
Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two…
Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. While Large Language Models (LLMs) have advanced this field,…
Real-world data often have an open long-tailed distribution, and building a unified QA model supporting various tasks is vital for practical QA applications. However, it is non-trivial to extend previous QA approaches since they either…
Tabular data is difficult to analyze and to search through, yielding for new tools and interfaces that would allow even non tech-savvy users to gain insights from open datasets without resorting to specialized data analysis tools or even…
Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the document into text for processing by Large Language Models…
Large Language Models (LLMs), although powerful in general domains, often perform poorly on domain-specific tasks such as medical question answering (QA). In addition, LLMs tend to function as "black-boxes", making it challenging to modify…
Current general-purpose large language models (LLMs) commonly exhibit knowledge hallucination and insufficient domain-specific adaptability in domain-specific tasks, limiting their effectiveness in specialized question answering scenarios.…
Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the identification of efficient and safe interventions. However,…
Table Question Answering (TableQA) poses a significant challenge for large language models (LLMs) because conventional linearization of tables often disrupts the two-dimensional relationships intrinsic to structured data. Existing methods,…
Healthcare question answering assistance aims to provide customer healthcare information, which widely appears in both Web and mobile Internet. The questions usually require the assistance to have proficient healthcare background knowledge…
Large language models (LLMs) achieve optimal utility when their responses are grounded in external knowledge sources. However, real-world documents, such as annual reports, scientific papers, and clinical guidelines, frequently combine…
Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them. Existing methods fail when faced with even minor variations in appearance. Here, we present DVQA, a dataset that tests many aspects of…
Large-scale language models (LLMs) have achieved remarkable success across various language tasks but suffer from hallucinations and temporal misalignment. To mitigate these shortcomings, Retrieval-augmented generation (RAG) has been…
Tabular question answering (TQA) presents a challenging setting for neural systems by requiring joint reasoning of natural language with large amounts of semi-structured data. Unlike humans who use programmatic tools like filters to…