mlsanityData to 14 Oct 2026

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

arXiv 2411.02959 ↗First posted 5 Nov 2024cs.IRcited by 37

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the hallucination problem of LLMs. The Web is a major source of external knowledge used in RAG systems, and many commercial RAG systems have used Web search engines as their major retrieval systems. Typically, such RAG systems retrieve search results, download HTML sources of the results, and then extract plain texts from the HTML sources. Plain text documents or chunks are fed into the LLMs to augment the generation. However, much of the structural and semantic information inherent in HTML, such as headings and table structures, is lost during this plain-text-based RAG process. To alleviate this problem, we propose HtmlRAG, which uses HTML instead of plain text as the format of retrieved knowledge in RAG. We believe HTML is better than plain text in modeling knowledge in external documents, and most LLMs possess robust capacities to understand HTML. However, utilizing HTML presents new challenges. HTML contains additional content such as tags, JavaScript, and CSS specifications, which bring extra input tokens and noise to the RAG system. To address this issue, we propose HTML cleaning, compression, and a two-step block-tree-based pruning strategy, to shorten the HTML while minimizing the loss of information. Experiments on six QA datasets confirm the superiority of using HTML in RAG systems.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 41 of its 85 references that are in the map. First posted on arXiv 5 Nov 2024.

Builds on

41 of 85 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research22 May

Other references · 40

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  9. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  10. 2019ELI5: Long Form Question Answeringcited by 575
  11. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 563
  12. 2023Active Retrieval Augmented Generationcited by 516
28 more
  1. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  2. 2023Language Models can Solve Computer Taskscited by 372
  3. 2024∞Bench: Extending Long Context Evaluation Beyond 100K Tokenscited by 367
  4. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  5. 2023Understanding Catastrophic Forgetting in Language Models via Implicit Inferencecited by 144
  6. 2019Fine-tune BERT for Extractive Summarizationcited by 122
  7. 2021WebSRC: A Dataset for Web-Based Structural Reading Comprehensioncited by 100
  8. 2021StructuralLM: Structural Pre-training for Form Understandingcited by 91
  9. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  10. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  11. 2023Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filteringcited by 65
  12. 2023Extractive Summarization via ChatGPT for Faithful Summary Generationcited by 59
  13. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  14. 2023SummIt: Iterative Text Summarization via ChatGPTcited by 54
  15. 2022Bidirectional Language Models Are Also Few-shot Learnerscited by 48
  16. 2023A Survey on Long Text Modeling with Transformerscited by 47
  17. 2022WebFormer: The Web-page Transformer for Structure Information Extractioncited by 34
  18. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  19. 2024Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Modelscited by 29
  20. 2024BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidencecited by 28
  21. 2024INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuningcited by 20
  22. 2024CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Taskscited by 18
  23. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generationcited by 16
  24. 2024Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embeddingcited by 13
  25. 2022XDoc: Unified Pre-training for Cross-Format Document Understandingcited by 12
  26. 2024CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generationcited by 8
  27. 2024ReALM: Reference Resolution As Language Modelingcited by 7
  28. 2024DocTabQA: Answering Questions from Long Documents Using Tablescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 18; 2026: 17.

37 papers.

Sort:

By area:

  1. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  2. 2025Agentic Entropy-Balanced Policy Optimizationcited by 40
  3. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 36
  4. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  5. 2025ReaderLM-v2: Small Language Model for HTML to Markdown and JSONcited by 15
  6. 2025Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Datacited by 10
  7. 2025HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputscited by 9
  8. 2025HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searchescited by 7
  9. 2025Source Coverage and Citation Bias in LLM-based vs. Traditional Search Enginescited by 6
  10. 2026Enhancing Web Agents with a Hierarchical Memory Treecited by 6
  11. 2026SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimizationcited by 5
  12. 2025Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutionscited by 2
25 more
  1. 2025Optimizing open-domain question answering with graph-based retrieval augmented generationcited by 2
  2. 2025Affordance Representation and Recognition for Autonomous Agentscited by 2
  3. 2025WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Webcited by 2
  4. 2025An Index-based Approach for Efficient and Effective Web Content Extractioncited by 2
  5. 2026PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generationcited by 2
  6. 2024Automatically Detecting Online Deceptive Patternscited by 1
  7. 2025CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documentscited by 1
  8. 2025Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environmentcited by 1
  9. 2025Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?cited by 1
  10. 2026AXE: Low-Cost Cross-Domain Web Structured Information Extractioncited by 1
  11. 2026PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systemscited by 1
  12. 2026SPIRE: Structure-Preserving Interpretable Retrieval of Evidencecited by 1
  13. 2026On the impact of retrieved content representations in RAG Pipelinescited by 1
  14. 2025SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrievalcited by 0
  15. 2025SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learningcited by 0
  16. 2026ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generationcited by 0
  17. 2026Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problemcited by 0
  18. 2026LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systemscited by 0
  19. 2026Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selectioncited by 0
  20. 2026Do Data Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrievalcited by 0
  21. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0
  22. 2026Co-Scraper: query-aware DOM Pruning and Reusable Scraper Synthesis for Lightweight Web Data Extractioncited by 0
  23. 2026PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphscited by 0
  24. 2026news-crawler-LM: A Small Long-Context Model For High-Quality News Crawlingcited by 0
  25. 2026LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Textcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Dynamic and Parametric Retrieval-Augmented Generation
  2. 2025UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation
  3. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation System
  4. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  5. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
  6. 2024Observations on Building RAG Systems for Technical Documents
  7. 2024Graph Retrieval-Augmented Generation: A Survey
  8. 2025RAG-Anything: All-in-One RAG Framework