Retrieval Augmented Generation

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge sources to improve accuracy and address limitations like hallucinations. Current research focuses on optimizing retrieval strategies (e.g., using hierarchical graphs, attention mechanisms, or determinantal point processes for diverse and relevant information selection), improving the integration of retrieved information with LLM generation (e.g., through various prompting techniques and model adaptation methods), and mitigating biases and ensuring fairness in RAG systems. The impact of RAG is significant, improving performance on various tasks like question answering and enabling more reliable and contextually aware applications across diverse domains, including healthcare and scientific research.

Papers

October 15, 2024

Retrieval Augmented Spelling Correction for E-Commerce Applications
Xuan Guo, Rohit Patki, Dante Everaert, Christopher Potts
Large Language Model Retrieval Augmented Generation E Commerce Retrieval Augmented Spelling Correction
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
Zhongxiang Sun, Xiaoxue Zang, Kai Zheng, Yang Song, Jun Xu, Xiao Zhang, Weijie Yu, Yang Song, Han Li
Retrieval Augmented Generation Hallucination Detection External Knowledge Mechanistic Interpretability Parametric Knowledge
Self-adaptive Multimodal Retrieval-Augmented Generation
Wenjia Zhai
Retrieval Augmented Generation Retrieval Augmented Retrieval Performance Multimodal Context Modal Adapter
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
Xinping Zhao, Dongfang Li, Yan Zhong, Boren Hu, Yibin Chen, Baotian Hu, Min Zhang
Retrieval Augmented Generation Faithful Generation Rule Reasoning Evidence Extraction
On the Capacity of Citation Generation by Large Language Models
Haosheng Qian, Yixing Fan, Ruqing Zhang, Jiafeng Guo
Large Language Model Retrieval Augmented Generation Response Generation Capacity Loss Citation Generation

October 14, 2024

Can Structured Data Reduce Epistemic Uncertainty?
Shriram M S, Sushmitha S, Gayathri K S, Shahina A
Deep Learning Model Retrieval Augmented Generation Epistemic Uncertainty Structured Data Ontology Alignment Contextual Similarity
FLARE: Faithful Logic-Aided Reasoning and Exploration
Erik Arakelyan, Pasquale Minervini, Pat Verga, Patrick Lewis, Isabelle Augenstein
Language Model Retrieval Augmented Generation Question Answering Environment Exploration Reasoning Benchmark Symbolic Solver
Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs
Haozhen Zhang, Tao Feng, Jiaxuan You
Graph Drawing Raw Data Retrieval Augmented Generation Retrieval Augmented Summarization Task Long Text Summarization
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
Retrieval Augmented Generation Faithful Generation Multi Modality Document Relevance Multimodal Chart
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
Naman Gupta, Shashank Kirtania, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares
Retrieval Augmented Generation Human Feedback Knowledge Editing Textual Structure Feed Ranking Centralized Reinforcement Learning
KBLaM: Knowledge Base augmented Language Model
Xi Wang, Liana Mikaelyan, Taketomo Isazawa, James Hensman
Language Model Context Learning Retrieval Augmented Generation Knowledge Base
Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning
Yongxin Xu, Ruizhe Zhang, Xinke Jiang, Yujie Feng, Yuzhen Xiao, Xinyu Ma, Runchuan Zhu, Xu Chu, Junfeng Zhao, Yasha Wang
Language Model Retrieval Augmented Generation Hyper Tune Knowledge Selection Hallucination Dataset Guideline Adherence Decoupling Degradation
EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
Zhangchi Feng, Dongdong Kuang, Zhongyuan Wang, Zhijie Nie, Yaowei Zheng, Richong Zhang
Retrieval Augmented Generation Network Programming LLM Response Sparse Retrieval Inference Acceleration Automated System Generation Framework
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
Xinping Zhao, Yan Zhong, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Dongfang Li, Baotian Hu, Min Zhang
Retrieval Augmented Generation Retrieval Performance Efficient Retrieval Information Funnel
Audio Captioning via Generative Pair-to-Pair Retrieval with Refined Knowledge Base
Choi Changin, Lim Sungjun, Rhee Wonjong
Retrieval Augmented Generation Knowledge Base Audio Captioning Generative Retrieval Audio Text Pair
Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations
Garima Agrawal, Sashank Gummuluri, Cosimo Spera
Retrieval Augmented Generation Yes No Question LLM Agent Community Conversation Answer Generation Question Classification User Query Augmented Agent

October 13, 2024

Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learning
Pengfei Jin, Peng Shu, Sekeun Kim, Qing Xiao, Sifan Song, Cheng Chen, Tianming Liu, Xiang Li, Quanzheng Li
Fine Tuning Retrieval Augmented Generation App to App Retrieval Zero Shot Learning Model Performance Model Adaptation
Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
Xinxi Chen, Li Wang, Wei Wu, Qi Tang, Yiyao Liu
Language Model Knowledge Graph Retrieval Augmented Generation Trustworthy Artificial Intelligence Reducing Hallucination

October 12, 2024

Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation
David Beauchemin, Zachary Gagnon, Ricahrd Khoury
Retrieval Augmented Generation Large Corpus Faithful Generation State of the Art LLM LLM Generated Question
Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
Guanting Dong, Xiaoshuai Song, Yutao Zhu, Runqi Qiao, Zhicheng Dou, Ji-Rong Wen
Retrieval Augmented Generation Faithful Generation Evaluation Framework Instruction Quality Graph Based Robotic Instruction Decomposer

Retrieval Augmented Generation

Papers

Retrieval Augmented Spelling Correction for E-Commerce Applications

ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

Self-adaptive Multimodal Retrieval-Augmented Generation

SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation

On the Capacity of Citation Generation by Large Language Models

Can Structured Data Reduce Epistemic Uncertainty?

FLARE: Faithful Logic-Aided Reasoning and Exploration

Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack

KBLaM: Knowledge Base augmented Language Model

Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG

Audio Captioning via Generative Pair-to-Pair Retrieval with Refined Knowledge Base

Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations

Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learning

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG

Quebec Automobile Insurance Question-Answering With Retrieval-Augmented Generation

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation