Top Research Papers on Retrieval Augmented Generation

A RAG task categorization method is proposed, classifying user queries into four levels based on the type of external data required and primary focus of the task: explicit fact queries, implicit fact queries, interpretable rationale queries, and hidden rationale queries.

A new paradigm for enhancing bibliometric analysis and knowledge retrieval in urban research is introduced, positioning an AI agent as a powerful tool for advancing research evaluation and understanding.

The RAG pipeline greatly enhanced overall performance of Llama-3 from 57.50% to 81.50% and GPT-4-turbo' s accuracy increased from 80.38% to 91.92% on BCSC and from 77.69% to 88.65 % on OphthoQuestions.

Retrieval-Augmented Generation (RAG) has gained significant attention from many researchers as an effective solution to address the hallucination issue of Foundational Models (FMs), particularly Large Language Models (LLMs). Although the RAG framework is considered a successful approach for enhancing LLMs by providing a suitable retrieval mechanism to obtain appropriate external knowledge, it still has limitations in acquiring high-quality knowledge from diverse data sources. The complementary integration of RAG and data spaces is proposed to exploit RAG’s capabilities within data spaces. Data...

The study explores the basic architecture of RAG, focusing on how retrieval and generation are integrated to handle knowledge-intensive tasks, and examines ongoing challenges such as scalability, bias, and ethical concerns in deployment.

Recently, Large Language Models (LLMs) and Foundation Models (FMs) have become prevalent for time series forecasting tasks. However, fine-tuning large language models (LLMs) for forecasting enables the adaptation to specific domains but may not generalize well across diverse, unseen datasets. Meanwhile, existing time series foundation models (TSFMs) lack inherent mechanisms for domain adaptation and suffer from limited interpretability, making them suboptimal for zero-shot forecasting. To this end, we present TS-RAG, a retrieval-augmented generation based time series forecasting framework that...

This work presents a novel architecture for building Retrieval-Augmented Generation (RAG) systems to improve Question Answering (QA) tasks from a target corpus and introduces QuIM-RAG (Question-to-question Inverted Index Matching), a novel approach for the retrieval mechanism in this system.

BACKGROUND Dietary supplements (DSs) are widely used to improve health and nutrition, but challenges related to misinformation, safety, and efficacy persist due to less stringent regulations compared with pharmaceuticals. Accurate and reliable DS information is critical for both consumers and health care providers to make informed decisions. OBJECTIVE This study aimed to enhance DS-related question answering by integrating an advanced retrieval-augmented generation (RAG) system with the integrated Dietary Supplement Knowledgebase 2.0 (iDISK2.0), a dietary supplement knowledge base, to improv...

Retail-GPT engages in human-like conversations, interprets user demands, checks product availability, and manages cart operations, aiming to serve as a virtual sales agent and test the viability of such assistants across different retail businesses.

RTK_RAG, a framework that integrates retrieval-augmented generation (RAG) and utilizes protein language models (PLMs) with a multiwindow convolutional neural network (MCNN) architecture to improve ATP binding site prediction for RTKs, demonstrates the potential of RAG-based frameworks for enhancing functional predictions in specialized protein families.

This work proposes a novel LLM-centric approach that integrates IR systems with LLMs to support multi-round RAG through learning Inner Monologues, and introduces a Refiner that improves the outputs from the Retriever, effectively bridging the gap between the Reasoner and IR modules with varying capabilities and fostering multi-round communications.

Document processing and query generation tasks in customs declaration scenarios face key challenges such as the complexity of multimodal data, adaptability to dynamic regulations, and ambiguity in query semantics. This study proposes a Retrieval-Augmented Generation system (ICCA-RAG) that addresses the core issues of processing complex customs documents and dynamically generating queries through multimodal document parsing, sparse-dense hybrid storage, and context-driven large language model generation. In terms of multimodal document parsing, the system supports comprehensive parsing of PDFs,...

A novel method is introduced, GeAR, which not only improves the global document-query similarity through contrastive learning, but also integrates well-designed fusion and decoding modules, which enables GeAR to generate relevant context within the documents based on a given query, facilitating learning to retrieve local fine-grained information.

This work introduces RAGAs (Retrieval Augmented Generation Assessment), a framework for reference-free evaluation of Retrieval Augmented Generation pipelines, and posit that such a framework can contribute crucially to faster evaluation cycles of RAG architectures, which is especially important given the fast adoption of LLMs.

A conceptual framework that integrates Generative AI and Retrieval-Augmented Generation with the principles of strategic engineering to enhance urban planning simulations and promises to transform urban planning into a more adaptive, inclusive and resilient practice.

The study concluded that open-source RAG-based systems offer a cost-effective solution for libraries to enhance information retrieval and transform libraries into dynamic information services.

The proposed CRP-RAG framework employs reasoning graphs to model complex query reasoning processes more comprehensively and accurately, and guides knowledge retrieval, aggregation, and evaluation through reasoning graphs, dynamically adjusting the reasoning path based on evaluation results and selecting knowledge-sufficiency paths for answer generation.

Techniques are provided to enhance the functions of a retrieval augmented generation (RAG) mechanism for a large language model (LLM). A Federated Learning (FL)-enhanced RAG (FLERAG) mechanism is provided that can account for relevant context-enhancing data from the retrieval process, as well as most recent data from the FL on which a large language model (LLM) may not have been trained. Using FLERAG, the output generation is determined through a scoring or ranking method that indicates whether the response from the LLM or the FL model is most accurate and relevant. This generated response is ...

This paper introduces a Hybrid Parameter-Adaptive RAG (HyPA-RAG) system tailored for AI legal and policy, exemplified by NYC Local Law 144, addressing the need for adaptable NLP systems in complex, high-stakes AI legal and policy applications.

An LLM-powered AI chatbot is developed that augments the answers that are produced with information from the course materials and highlights that both support mechanisms are seen as useful and that support mechanisms work well for specific tasks, while less so for other tasks.