Kg Rag

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge bases to improve accuracy and reduce hallucinations, a significant challenge in current LLMs. Research focuses on improving retrieval methods, such as optimizing query rewriting and employing knowledge graphs, and enhancing the integration of retrieved information with LLM generation, including exploring novel architectures like interleaved retrieval and generation. These advancements are crucial for building more reliable and trustworthy LLMs, with applications ranging from improved customer service chatbots to more accurate question-answering systems in specialized domains.

Papers

November 7, 2024

Enhancing classroom teaching with LLMs and RAG
Elizabeth A Mullins, Adrian Portillo, Kristalys Ruiz-Rohena, Aritran Piplai
Medical LLM Answer Correctness Kg Rag Educational Resource Expert Driven Cybersecurity Instruction

October 21, 2024

Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report
Ayman Asad Khan, Md Toufique Hasan, Kai Kristian Kemell, Jussi Rasku, Pekka Abrahamsson
Retrieval Augmented Generation Information Retrieval Response Generation eXperience Report Generative AI System LLM Integrated Application PDF Document Kg Rag Augmented Generation

October 15, 2024

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG
Jinyoung Kim, Dayoon Ko, Gunhee Kim
Knowledge Base Continual Adaptation Kg Rag Entity Typing Textual Mention

October 3, 2024

A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
Shailja Gupta, Rajesh Ranjan, Surya Narayan Singh
Natural Language Processing Retrieval Augmented Generation Comprehensive Survey Generative Language Model Future Direction Retrieval Augmented Language Model Current State Kg Rag

September 30, 2024

Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG
Chenhao Fang, Derek Larson, Shitong Zhu, Sophie Zeng, Wendy Summer, Yanqing Peng, Yuriy Hulovatyy, Rajeev Rao, Gabriel Forgues, Arya Pudota, Alex Goncalves, Hervé Robert
Continual Pre Training Kg Rag Reducing Hallucination

September 5, 2024

RAG based Question-Answering for Contextual Response Prediction System
Sriram Veturi, Saurabh Vaichal, Nafis Irtiza Tripto, Reshma Lal Jagadheesh, Nian Yan
Retrieval Augmented Generation Context Aware Question Answering System Kg Rag Question Answering Framework

August 30, 2024

MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models
Yujing Wang, Hainan Zhang, Liang Pang, Liang Pang, Hongwei Zheng, Zhiming Zheng
Large Language Model Query Information Response Generation Kg Rag Multi Point Feedback

August 12, 2024

A New Pipeline For Generating Instruction Dataset via RAG and Self Fine-Tuning
Chih-Wei Song, Yu-Kai Lee, Yin-Te Tsai
Large Language Model Language Model Fine Tuning Domain Specific Pipeline System Instruction Dataset Domain Corpus Kg Rag

August 6, 2024

FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG
Sai Puppala, Ismail Hossain, Md Jahangir Alam, Sajedul Talukder
Federated Learning Social Medium LLM Based Social Network Federated Prompt Cooperation Kg Rag Query Processing

July 30, 2024

From Feature Importance to Natural Language Explanations Using LLMs with RAG
Sule Tekkesinoglu, Lars Kunze
Large Language Model Question Answering Natural Language Explanation Feature Importance Semantic Feature Kg Rag Natural Language Expression Human Explanation

July 10, 2024

Examining Long-Context Large Language Models for Environmental Review Document Comprehension
Hung Phan, Anurag Acharya, Rounak Meyur, Sarthak Chaturvedi, Shivam Sharma, Mike Parker, Dan Nally, Ali Jannesari, Karl Pazdernik, Mahantesh Halappanavar, Sai Munikoti, Sameera Horawalavithana
Language Model Long Context Long Context Large Language Model Question Answering System Policy Adaptation Kg Rag

June 29, 2024

From RAG to RICHES: Retrieval Interlaced with Sequence Generation
Palak Jain, Livio Baldini Soares, Tom Kwiatkowski
Large Corpus App to App Retrieval Multi Hop Sequence Generation Generating Rich Sequence Generation Task Kg Rag

June 23, 2024

FS-RAG: A Frame Semantics Based Approach for Improved Factual Accuracy in Large Language Models
Harish Tayyar Madabushi
Large Language Model Retrieval Augmented Generation Kg Rag Semantic Frame Semantic Retrieval

June 19, 2024

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
Jinhyuk Lee, Anthony Chen, Zhuyun Dai, Dheeru Dua, Devendra Singh Sachan, Michael Boratko, Yi Luan, Sébastien M. R. Arnold, Vincent Perot, Siddharth Dalmia, Hexiang Hu, Xudong Lin, Panupong Pasupat, Aida Amini, Jeremy R. Cole, Sebastian Riedel, Iftekhar Naim, Ming-Wei Chang, Kelvin Guu
Large Corpus Context Length Long Context Language State of the Art Retrieval Context Retrieval Kg Rag

May 26, 2024

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
Jiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang
Large Language Model Language Model KV Cache Kg Rag

May 25, 2024

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
Yun Zhu, Jia-Chen Gu, Caitlin Sikora, Ho Ko, Yinxiao Liu, Chu-Cheng Lin, Lei Shu, Liangchen Luo, Lei Meng, Bang Liu, Jindong Chen
Large Language Model Retrieval Augmented Generation Kg Rag RAG Based Sparse Mechanism

May 21, 2024

The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)
Yucheng Cai, Si Chen, Yuxuan Wu, Yi Huang, Junlan Feng, Zhijian Ou
Retrieval Augmented Generation Dialog System Kg Rag M2MeT Challenge

May 20, 2024

KG-RAG: Bridging the Gap Between Knowledge and Creativity
Diego Sanmartin
Large Language Model Knowledge Graph Knowledge Based Sustained Creativity Knowledge Intensive Task Knowledge Graph Question Answering Kg Rag Graph Retrieval Augmented Generation

April 22, 2024

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations
Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang, Jong C. Park
Native Robustness Retrieval Augmented Generation Attack Success Rate Recent Large Language Model Kg Rag RAG Based Document Generation Typo Squatting

April 18, 2024

RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation
Chao Jin, Zili Zhang, Xuanlin Jiang, Fangyue Liu, Xin Liu, Xuanzhe Liu, Xin Jin
Large Language Model Retrieval Augmented Generation LLM Inference Long Sequence Kg Rag Knowledge Storage

Kg Rag

Papers

Enhancing classroom teaching with LLMs and RAG

Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG

A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions

Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG

RAG based Question-Answering for Contextual Response Prediction System

MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models

A New Pipeline For Generating Instruction Dataset via RAG and Self Fine-Tuning

FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG

From Feature Importance to Natural Language Explanations Using LLMs with RAG

Examining Long-Context Large Language Models for Environmental Review Document Comprehension

From RAG to RICHES: Retrieval Interlaced with Sequence Generation

FS-RAG: A Frame Semantics Based Approach for Improved Factual Accuracy in Large Language Models

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection

The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)

KG-RAG: Bridging the Gap Between Knowledge and Creativity

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations

RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation