Image de couverture de livre

MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shin, Joongmin, Park, Chanjun, Park, Jeongbae, Seo, Jaehyung, Lim, Heuiseok
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models
par: Shin, Joongmin, et autres
Publié: (2026)

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
par: Shin, Joongmin, et autres
Publié: (2026)

CoME: An Unlearning-based Approach to Conflict-free Model Editing
par: Jung, Dahyun, et autres
Publié: (2025)

ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction
par: Park, Jeiyoon, et autres
Publié: (2024)

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
par: Park, Jeiyoon, et autres
Publié: (2024)

MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation
par: Park, Chanhee, et autres
Publié: (2025)

KITE: A Benchmark for Evaluating Korean Instruction-Following Abilities in Large Language Models
par: Kim, Dongjun, et autres
Publié: (2025)

Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models
par: Moon, Hyeonseok, et autres
Publié: (2024)

The Impact of Negated Text on Hallucination with Large Language Models
par: Seo, Jaehyung, et autres
Publié: (2025)

Call for Rigor in Reporting Quality of Instruction Tuning Data
par: Moon, Hyeonseok, et autres
Publié: (2025)

No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand
par: Jung, Jimin, et autres
Publié: (2026)

Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse
par: Lee, Seungyoon, et autres
Publié: (2024)

FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models
par: Jung, Dahyun, et autres
Publié: (2025)

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
par: Jang, Youngjoon, et autres
Publié: (2025)

Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks
par: Kim, Dongjun, et autres
Publié: (2025)

Translation of Multifaceted Data without Re-Training of Machine Translation Systems
par: Moon, Hyeonseok, et autres
Publié: (2024)

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism
par: Park, Chanjun, et autres
Publié: (2024)

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
par: Chun, Yongchan, et autres
Publié: (2026)

Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models
par: Park, Hyunbyung, et autres
Publié: (2024)

InstaTrans: An Instruction-Aware Translation Framework for Non-English Instruction Datasets
par: Kim, Yungi, et autres
Publié: (2024)

Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard
par: Park, Chanjun, et autres
Publié: (2024)

LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models
par: Kim, Yungi, et autres
Publié: (2024)

Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline
par: Koo, Seonmin, et autres
Publié: (2024)

Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue
par: Park, Jeiyoon, et autres
Publié: (2022)

Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
par: Eo, Sugyeong, et autres
Publié: (2025)

HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking
par: Lu, Wensheng, et autres
Publié: (2025)

ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction
par: Jung, Jeesu, et autres
Publié: (2025)

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
par: Park, Hyeongcheol, et autres
Publié: (2025)

NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models
par: Moon, Hyeonseok, et autres
Publié: (2025)

Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
par: Eo, Sugyeong, et autres
Publié: (2026)

LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
par: Deng, Chao, et autres
Publié: (2024)

Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering
par: Chen, Huiyao, et autres
Publié: (2025)

Sensory-Aware Sequential Recommendation via Review-Distilled Representations
par: Yoon, Yeo Chan, et autres
Publié: (2026)

Adaptive Chunking: Optimizing Chunking-Method Selection for RAG
par: Júnior, Paulo Roberto de Moura, et autres
Publié: (2026)

LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
par: Kim, Dongjun, et autres
Publié: (2026)

SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
par: Zhang, Xuechen, et autres
Publié: (2025)

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
par: Wang, Minzheng, et autres
Publié: (2024)

Who speaks like a style of Vitamin: Towards Syntax-Aware DialogueSummarization using Multi-task Learning
par: Lee, Seolhwa, et autres
Publié: (2021)

Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
par: Chun, Yongchan, et autres
Publié: (2025)

Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking
par: Nguyen, Hai Toan, et autres
Publié: (2025)