Related papers: SQuARE: Structured Query & Adaptive Retrieval Engi…

Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity…

Understanding the meaning of a text is a fundamental challenge of natural language understanding (NLU) and from its early days, it has received significant attention through question answering (QA) tasks. We introduce a general…

Question Answering (QA) systems are increasingly deployed in applications where they support real-world decisions. However, state-of-the-art models rely on deep neural networks, which are difficult to interpret by humans. Inherently…

In the rapidly evolving field of Natural Language Processing, Large Language Models (LLMs) are tasked with increasingly complex reasoning challenges. Traditional methods like chain-of-thought prompting have shown promise but often fall…

Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for…

Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain,…

Vector similarity search presents significant challenges in terms of scalability for large and high-dimensional datasets, as well as in providing native support for hybrid queries. Serverless computing and cloud functions offer attractive…

Scientific reasoning increasingly requires linking structured experimental data with the unstructured literature that explains it, yet most large language model (LLM) assistants cannot reason jointly across these modalities. We introduce…

Table retrieval, essential for accessing information through tabular data, is less explored compared to text retrieval. The row/column structure and distinct fields of tables (including titles, headers, and cells) present unique challenges.…

Querying both structured and unstructured data has become a new paradigm in data analytics and recommendation. With unstructured data, such as text and videos, are converted to high-dimensional vectors and queried with approximate nearest…

We present the design of a structured search engine which returns a multi-column table in response to a query consisting of keywords describing each of its columns. We answer such queries by exploiting the millions of tables on the Web…

Text-to-SQL technology has evolved rapidly, with diverse academic methods achieving impressive results. However, deploying these techniques in real-world systems remains challenging due to limited integration tools. Despite these advances,…

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with retrieving contextually relevant information,…

Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. [1] presented the first systematic evaluation comparing vector-based agentic RAG against…

The continuous development of Question Answering (QA) datasets has drawn the research community's attention toward multi-domain models. A popular approach is to use multi-dataset models, which are models trained on multiple datasets to…

A large amount of information is stored in data tables. Users can search for data tables using a keyword-based query. A table is composed primarily of data values that are organized in rows and columns providing implicit structural…

Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external knowledge retrieval. However, we find that existing approaches rarely…

Retrieval-Augmented Generation (RAG) systems for financial document question answering typically follow a chunk-based paradigm: documents are split into fragments, embedded into vector space, and retrieved via similarity search. While…

Clinical prediction from structured electronic health records (EHRs) is challenging due to high dimensionality, heterogeneity, class imbalance, and distribution shift. While tabular in-context learning (TICL) and retrieval-augmented methods…