Top RAG Papers of the Week (October Week 2, 2024)

[1] EasyRAG

This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. EasyRAG has three advantages namely, accurate question answering, simple deployment and efficient inference.?[Tweet] and [Paper]

[2] Vision-based RAG

This paper presents VisRAG which involves embedding the document using a VLM as an image and then retrieving it to enhance the generation of a VLM. When compared to traditional text-based RAG, VisRAG maximizes the retention and utilization of the data information in the original documents, eliminating the information loss introduced during the parsing process. VisRAG outperforms traditional RAG in both the retrieval and generation stages, achieving a 25–39% end-to-end performance gain over traditional textbased RAG pipeline. [Tweet] and [Paper]

[3] FunnelRAG

This paper presents a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG. FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent. [Tweet] and [Paper]

[4] CoFE-RAG

This paper presents CoFE-RAG,? a Comprehensive Full-chain Evaluation framework to facilitate thorough evaluation across the entire RAG pipeline, including chunking, retrieval, reranking, and generation. CoFE-RAG provides unique insights into the effectiveness of RAG systems in handling diverse data scenarios.?[Tweet] and [Paper]

[5] RAG-based Spelling Correction

This paper presents a RAG-based spelling correction approach for E-Commerce applications. On this approach, product names are retrieved from a catalog and incorporated into the context used by a large language model (LLM) that has been fine-tuned to do contextual spelling correction. Results show improvements in spelling correction utilizing the RAG framework beyond a stand-alone LLM.? [Tweet] and [Paper]

[6] Multilingual RAG Benchmark

This paper introduces MIRAGE-Bench, a standardized arena-based multilingual RAG benchmark for 18 diverse languages on Wikipedia. The benchmark is constructed using MIRACL, a retrieval dataset, and extended for multilingual generation evaluation. Results show that proprietary and large open-source LLMs currently dominate in multilingual RAG. [Tweet] and [Paper]

[7] Assessing RAG Models for Health Chatbots

This paper presents an extensive assessment of 24 LLMs on real world data collected from Indian patients interacting with a medical chatbot in Indian English and 4 other Indic languages. Results show that (1) models vary significantly in their performance (2) instruction tuned Indic models do not always perform well on Indic language queries and (3) factual correctness is generally lower for responses to Indic queries compared to English queries.?[Tweet] and [Paper]

[8] Medical Multimodal RAG System

This paper presents MMed-RAG, a versatile multimodal RAG system, designed to enhance the factuality of Med-LVLMs. MMed-RAG can achieve an average improvement of 43.8% in the factual accuracy of Med-LVLMs.? [Tweet] and [Paper]

Do subscribe to the newsletter so that you won't miss interesting updates related to Generative AI, LLMs and RAG.

Kalyan KS, Research Scientist(NLP) at Akmmus AI Labs.