llm_rag.md

LLM Rag

• LLM Rag
  • Survey
  • RAG
  • Multi Modal
  • Embedding
  • Evaluation
  • Database
  • Projects
  • Products
  • Misc
  • Vector Database

Survey

RAG

• Knowledge Models Combine Retrieval with Generation: An Introduction to RAG

• Personalized Graph-Based Retrieval for Large Language Models, arXiv, 2501.02157, arxiv, pdf, cication: -1

  Steven Au, Cameron J. Dimacali, Ojasmitha Pedirappagari, ..., Ryan A. Rossi, Nesreen K. Ahmed

• GeAR: Generation Augmented Retrieval, arXiv, 2501.02772, arxiv, pdf, cication: -1

  Haoyu Liu, Shaohan Huang, Jianfeng Liu, ..., Furu Wei, Qi Zhang

• Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks, arXiv, 2412.15605, arxiv, pdf, cication: -1

  Brian J Chan, Chao-Ting Chen, Jui-Hung Cheng, ..., Hen-Hsen Huang · (cag - hhhuang)

• Long Context vs. RAG for LLMs: An Evaluation and Revisits, arXiv, 2501.01880, arxiv, pdf, cication: -1

  Xinze Li, Yixin Cao, Yubo Ma, ..., Aixin Sun

• SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval, arXiv, 2412.15443, arxiv, pdf, cication: -1

  Aakash Mahalingam, Vinesh Kumar Gande, Aman Chadha, ..., Vinija Jain, Divya Chaudhary

• GemmaEmbed is a dense-vector embedding model, trained especially for retrieval. 🤗

• 🌟 Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference, arXiv, 2412.13663, arxiv, pdf, cication: -1

  Benjamin Warner, Antoine Chaffin, Benjamin Clavié, ..., Jeremy Howard, Iacopo Poli · (huggingface) · (𝕏)

• Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models, arXiv, 2411.19443, arxiv, pdf, cication: -1

  Tian Yu, Shaolei Zhang, Yang Feng · (Auto-RAG - ictnlp)

• NV-Embed-v2, a generalist embedding model that ranks No. 1 on the Massive Text Embedding Benchmark (MTEB benchmark) 🤗

  · (arxiv)

• Jina CLIP v2: Multilingual Multimodal Embeddings for Texts and Images 🤗

  · (huggingface)

• Long Term Memory: The Foundation of AI Self-Evolution, arXiv, 2410.15665, arxiv, pdf, cication: -1

  Xun Jiang, Feng Li, Han Zhao, ..., Mengdi Wang, Tianqiao Chen · (𝕏)

• Binary vector embeddings are so cool

• 🌟 HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems, arXiv, 2411.02959, arxiv, pdf, cication: -1

  Jiejun Tan, Zhicheng Dou, Wen Wang, ..., Weipeng Chen, Ji-Rong Wen

• M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding, arXiv, 2411.04952, arxiv, pdf, cication: -1

  Jaemin Cho, Debanjan Mahata, Ozan Irsoy, ..., Yujie He, Mohit Bansal · (m3docrag.github)

• In Defense of RAG in the Era of Long-Context Language Models, arXiv, 2409.01666, arxiv, pdf, cication: 3

  Tan Yu, Anbang Xu, Rama Akkiraju · (zyphra)

• Toward General Instruction-Following Alignment for Retrieval-Augmented Generation, arXiv, 2410.09584, arxiv, pdf, cication: -1

  Guanting Dong, Xiaoshuai Song, Yutao Zhu, ..., Zhicheng Dou, Ji-Rong Wen · (FollowRAG.github) · (arxiv) · (FollowRAG - dongguanting) · (huggingface)

• Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception, arXiv, 2410.12788, arxiv, pdf, cication: -1

  Jihao Zhao, Zhiyuan Ji, Pengnian Qi, ..., Feiyu Xiong, Zhiyu Li · (Meta-Chunking - IAAR-Shanghai) · (arxiv)

• Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free, arXiv, 2410.10814, arxiv, pdf, cication: -1

  Ziyue Li, Tianyi Zhou · (MoE-Embedding - tianyi-lab)

Multi Modal

• 🌟 VideoRAG: Retrieval-Augmented Generation over Video Corpus, arXiv, 2501.05874, arxiv, pdf, cication: -1

  Soyeong Jeong, Kangsan Kim, Jinheon Baek, ..., Sung Ju Hwang · (huggingface) · (𝕏)

• Visual Document Retrieval Goes Multilingual 🤗

  · (𝕏)

• MM-Embed, an extension of NV-Embed-v1 with multimodal retrieval capability. 🤗

• Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications, arXiv, 2410.21943, arxiv, pdf, cication: -1

  Monica Riedler, Stefan Langer · (x)

• VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents, arXiv, 2410.10594, arxiv, pdf, cication: -1

  Shi Yu, Chaoyue Tang, Bokai Xu, ..., Zhiyuan Liu, Maosong Sun

• Introducing Multimodal Embed 3: Powering AI Search

• MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models, arXiv, 2410.13085, arxiv, pdf, cication: -1

  Peng Xia, Kangyu Zhu, Haoran Li, ..., James Zou, Huaxiu Yao

Embedding

Evaluation

• OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain, arXiv, 2412.13018, arxiv, pdf, cication: -1

  Shuting Wang, Jiejun Tan, Zhicheng Dou, ..., Ji-Rong Wen · (OmniEval - RUC-NLPIR)

• Long Context RAG Performance of Large Language Models, arXiv, 2411.03538, arxiv, pdf, cication: -1

  Quinn Leng, Jacob Portes, Sam Havens, ..., Matei Zaharia, Michael Carbin

• CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation, arXiv, 2410.23090, arxiv, pdf, cication: -1

  Yiruo Cheng, Kelong Mao, Ziliang Zhao, ..., Ji-Rong Wen, Zhicheng Dou · (CORAL - Ariya12138)

Database

Projects

• pathway - pathwaycom

• onyx - onyx-dot-app

• fast-graphrag - circlemind-ai

• txtai - neuml

• Perplexica - ItzCrazyKns

• dsRAG - D-Star-AI

• 🌟 RAGViz - cxcscmu

  · (youtube)

• pgai - timescale

• Contextual RAG from Anthropic 𝕏

  · (together-cookbook - togethercomputer)

• AutoRAG - Marker-Inc-Korea

• KAG - OpenSPG

  Knowledge Augmented Generation

Products

Misc

• GraphRAG-esque metadata tagging + retrieval 𝕏

  · (llama_parse - run-llama)

• What is Agentic RAG

  · (𝕏)

• Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge 🤗

Vector Database