paper-with-me

Papers

Financial Report Chunking for Effective Retrieval Augmented Generation

2024-02-05 · Antonio Jimeno Yepes, Yao You, Jan Milczek, Sebastian Laverde, Renyu Li

Chunking information is a key step in Retrieval Augmented Generation (RAG). Current research primarily centers on paragraph-level chunking. This approach treats all texts as equal and neglects the information contained in the structure of documents. We propose an expanded approach to chunk documents by moving beyond mere paragraph-level chunking to chunk primary by structural element components of documents. Dissecting documents into these constituent elements creates a new way to chunk documents that yields the best chunk size without tuning. We introduce a novel framework that evaluates how chunking based on element types annotated by document understanding models contributes to the overall context and accuracy of the information retrieved. We also demonstrate how this approach impacts RAG assisted Question & Answer task performance. Our research includes a comprehensive analysis of various element types, their role in effective information retrieval, and the impact they have on the quality of RAG outputs. Findings support that element type based chunking largely improve RAG results on financial reporting. Through this research, we are also able to answer how to uncover highly accurate RAG.

📄 PDF Abstract BibTeX arXiv:2402.05131

Code (1)

EncryptedBinary/Meta_analysis pytorch

Tasks

Chunkingdocument understandingInformation RetrievalRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Weight Decay 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation

2026-02-27 · Zhengren Wang, Dongsheng Ma, Huaping Zhong, Jiayu Li 외 arxiv

The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a…

Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models

2025-11-22 · Elias Lumer, Matt Melich, Olivia Zino, Elena Kim 외 arxiv

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents.…

Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems

2026-01-08 · Uday Allu, Sonu Kedia, Tanmay Odapally, Biddwan Ahmed arxiv

Retrieval-Augmented Generation (RAG) systems critically depend on effective document chunking strategies to balance retrieval quality, latency, and operational cost. Traditional chunking approaches, such as fixed-size, r…

Text Generation

MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration

2026-05-24 · Magnus Samuelsen, Wilmer Nyström, Somnath Mazumdar, Mansoor Hussain 외 arxiv

Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (LLMs), a requirement for reliable, financial analysis where answers m…

Information Retrieval

HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking

2025-09-15 · Wensheng Lu, Keyu Chen, Ruizhi Qiao, Xing Sun arxiv

Retrieval-Augmented Generation (RAG) enhances the response capabilities of language models by integrating external knowledge sources. However, document chunking as an important part of RAG system often lacks effective ev…