mlsanityData to 7 Oct 2026

Advanced ingestion process powered by LLM parsing for RAG system

arXiv 2412.15262 ↗First posted 16 Dec 2024cs.CL cs.AI cs.IRcited by 1

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Retrieval Augmented Generation (RAG) systems struggle with processing multimodal documents of varying structural complexity. This paper introduces a novel multi-strategy parsing approach using LLM-powered OCR to extract content from diverse document types, including presentations and high text density files both scanned or not. The methodology employs a node-based extraction technique that creates relationships between different information types and generates context-aware metadata. By implementing a Multimodal Assembler Agent and a flexible embedding strategy, the system enhances document comprehension and retrieval capabilities. Experimental evaluations across multiple knowledge bases demonstrate the approach's effectiveness, showing improvements in answer relevancy and information faithfulness.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 4 of its 10 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

4 of 10 references.

References · 4

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  2. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  3. 2024Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generationcited by 23
  4. 2024Human interaction classifier for LLM based chatbotcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025CMRAG: Co-modality-based visual document retrieval and question answeringcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
  2. 2026Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines
  3. 2026MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
  4. 2025Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
  5. 2024Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications
  6. 2025Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval
  7. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
  8. 2024Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report