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

arXiv: https://arxiv.org/abs/2411.02959 · HTML: https://mlsanity.com/paper/2411.02959/

## 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.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 30 of 41)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- [Understanding Catastrophic Forgetting in Language Models via Implicit Inference](https://mlsanity.com/paper/2309.10105/) (2023)
- [Fine-tune BERT for Extractive Summarization](https://mlsanity.com/paper/1903.10318/) (2019)
- [WebSRC: A Dataset for Web-Based Structural Reading Comprehension](https://mlsanity.com/paper/2101.09465/) (2021)
- [StructuralLM: Structural Pre-training for Form Understanding](https://mlsanity.com/paper/2105.11210/) (2021)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering](https://mlsanity.com/paper/2304.12102/) (2023)
- [Extractive Summarization via ChatGPT for Faithful Summary Generation](https://mlsanity.com/paper/2304.04193/) (2023)
- [When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation](https://mlsanity.com/paper/2402.11457/) (2024)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [Bidirectional Language Models Are Also Few-shot Learners](https://mlsanity.com/paper/2209.14500/) (2022)
- [A Survey on Long Text Modeling with Transformers](https://mlsanity.com/paper/2302.14502/) (2023)
- [WebFormer: The Web-page Transformer for Structure Information Extraction](https://mlsanity.com/paper/2202.00217/) (2022)

## Built on by (most cited first, 30 of 37)

- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [Agentic Entropy-Balanced Policy Optimization](https://mlsanity.com/paper/2510.14545/) (2025)
- [A Survey on Knowledge-Oriented Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10677/) (2025)
- [RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation](https://mlsanity.com/paper/2412.11919/) (2024)
- [ReaderLM-v2: Small Language Model for HTML to Markdown and JSON](https://mlsanity.com/paper/2503.01151/) (2025)
- [Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data](https://mlsanity.com/paper/2503.05587/) (2025)
- [HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs](https://mlsanity.com/paper/2503.02003/) (2025)
- [HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches](https://mlsanity.com/paper/2508.08088/) (2025)
- [Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines](https://mlsanity.com/paper/2512.09483/) (2025)
- [Enhancing Web Agents with a Hierarchical Memory Tree](https://mlsanity.com/paper/2603.07024/) (2026)
- [SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization](https://mlsanity.com/paper/2602.12187/) (2026)
- [Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions](https://mlsanity.com/paper/2502.04389/) (2025)
- [Optimizing open-domain question answering with graph-based retrieval augmented generation](https://mlsanity.com/paper/2503.02922/) (2025)
- [Affordance Representation and Recognition for Autonomous Agents](https://mlsanity.com/paper/2510.24459/) (2025)
- [WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web](https://mlsanity.com/paper/2511.14182/) (2025)
- [An Index-based Approach for Efficient and Effective Web Content Extraction](https://mlsanity.com/paper/2512.06641/) (2025)
- [PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.28344/) (2026)
- [Automatically Detecting Online Deceptive Patterns](https://mlsanity.com/paper/2411.07441/) (2024)
- [CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents](https://mlsanity.com/paper/2505.17503/) (2025)
- [Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment](https://mlsanity.com/paper/2506.10030/) (2025)
- [Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?](https://mlsanity.com/paper/2509.25107/) (2025)
- [AXE: Low-Cost Cross-Domain Web Structured Information Extraction](https://mlsanity.com/paper/2602.01838/) (2026)
- [PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2603.25164/) (2026)
- [SPIRE: Structure-Preserving Interpretable Retrieval of Evidence](https://mlsanity.com/paper/2604.20849/) (2026)
- [On the impact of retrieved content representations in RAG Pipelines](https://mlsanity.com/paper/2605.30790/) (2026)
- [SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval](https://mlsanity.com/paper/2508.20778/) (2025)
- [SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning](https://mlsanity.com/paper/2510.01832/) (2025)
- [ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation](https://mlsanity.com/paper/2602.15189/) (2026)
- [Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem](https://mlsanity.com/paper/2602.18734/) (2026)
- [LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems](https://mlsanity.com/paper/2605.08305/) (2026)

## 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.