Related papers: Ultron: An Ultimate Retriever on Corpus with a Mod…

Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual…

Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the…

We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional…

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…

The text retrieval is the task of retrieving similar documents to a search query, and it is important to improve retrieval accuracy while maintaining a certain level of retrieval speed. Existing studies have reported accuracy improvements…

We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we…

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Document Question Answering (DocQA) focuses on answering questions grounded in given documents, yet existing DocQA agents lack effective tool utilization and largely rely on closed-source models. In this work, we introduce DocDancer, an…

Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reasonable overall performance, they often underperform models…

Generative retrieval (GR) reformulates the Information Retrieval (IR) task as the generation of document identifiers (docIDs). Despite its promise, existing GR models exhibit poor generalization to newly added documents, often failing to…

The Differentiable Search Index (DSI) is a novel information retrieval (IR) framework that utilizes a differentiable function to generate a sorted list of document identifiers in response to a given query. However, due to the black-box…

When experiencing an information need, users want to engage with a domain expert, but often turn to an information retrieval system, such as a search engine, instead. Classical information retrieval systems do not answer information needs…

Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate page-level content…

Despite significant progress in multimodal large language models (MLLMs), their performance on complex, multi-page document comprehension remains inadequate, largely due to the lack of high-quality, document-level datasets. While current…

Multi-label text classification (MLC) is a challenging task in settings of large label sets, where label support follows a Zipfian distribution. In this paper, we address this problem through retrieval augmentation, aiming to improve the…

Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle…

With the rapid development of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) has become a predominant method in the field of professional knowledge-based question answering. Presently, major foundation model companies…

A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain…