Results 31 to 40 of about 14,626 (158)

Resource-Constrained Evaluation of Quantized Local LLMs for Retrieval-Augmented Generation on a Reduced-Corpus Setting

IEEE Access
This paper studies retrieval-augmented generation (RAG) under a realistic local deployment constraint. Rather than proposing a new retriever or generator architecture, the paper evaluates how local, quantized RAG behaves when answer quality, provenance ...
Marcio L. Lima de Oliveira, Jes de Jesus Fiais Cerqueira   +1 more
doaj   +1 more source

Bridging the Question–Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings

IEEE Access
Retrieval-Augmented Generation (RAG) systems synergize retrieval mechanisms with generative language models to enhance the accuracy and relevance of responses. However, bridging the style gap between user queries and relevant information in document text
Domen Vake, Jernej Vicic, Aleksandar Tosic   +2 more
doaj   +1 more source

Corrective Retrieval Augmented Generation

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model ...
Shi-Qi Yan, Jia-Chen Gu, Yun Zhu, Zhen-Hua Ling   +3 more
openaire   +2 more sources

Multimodal retrieval-augmented generation framework for visually rich knowledge in the architecture domain

Architectural Intelligence
Architectural design relies heavily on rich and multimodal knowledge—including text descriptions, detailed tables, and complex visual information—to inform creative and technical decision-making.
Xianchuan Meng, Ziyu Tong
doaj   +1 more source

DC-RAG: a dual-channel retrieval-augmented generation framework for audit analysis

Scientific Reports
With the continuous growth of information retrieval and knowledge acquisition demands, intelligent question-answering systems have been widely adopted across various vertical domains.
Chunyu Xing, Hang Meng
doaj   +1 more source

LLM based QA chatbot builder: A generative AI-based chatbot builder for question answering

SoftwareX
Large language model (LLM) based interactive chatbots have been gaining popularity as a tool to serve organizational information among people. Building such a tool goes through several development phases i.e.
Md. Shahidul Salim, Sk Imran Hossain, Tanim Jalal, Dhiman Kumer Bose, Mohammad Jahid Ibna Basher   +4 more
doaj   +1 more source

Source Attribution in Retrieval-Augmented Generation

While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Large Language Models (LLMs), particularly within Retrieval-Augmented Generation (RAG) systems, is nascent and challenging.
Ikhtiyor Nematov, Tarik Kalai, Elizaveta Kuzmenko, Gabriele Fugagnoli, Dimitris Sacharidis, Katja Hose, Tomer Sagi   +6 more
openaire   +3 more sources

Evaluation of Retrieval-Augmented Generation: A Survey

Retrieval-Augmented Generation (RAG) has recently gained traction in natural language processing. Numerous studies and real-world applications are leveraging its ability to enhance generative models through external information retrieval. Evaluating these RAG systems, however, poses unique challenges due to their hybrid structure and reliance on ...
Hao Yu 0030, Aoran Gan, Kai Zhang 0038, Shiwei Tong, Qi Liu 0003, Zhaofeng Liu   +5 more
openaire   +2 more sources

CoRAG: Collaborative Retrieval-Augmented Generation

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
Retrieval-Augmented Generation (RAG) models excel in knowledge-intensive tasks, especially under few-shot learning constraints. We introduce CoRAG, a framework extending RAG to collaborative settings, where clients jointly train a shared model using a collaborative passage store.
Aashiq Muhamed, Mona T. Diab, Virginia Smith   +2 more
openaire   +2 more sources

Research on risk decision-making generation method for water conservancy project based on multimodal knowledge graph and large language model.

PLoS ONE
Traditional knowledge graphs of water conservancy project risks have supported risk decision-making. However, they are constrained by limited data modalities and low accuracy in information extraction.
Libo Yang, Yuan Li, Junhua Tan, Libo Mao
doaj   +1 more source