Results 41 to 50 of about 14,626 (158)

DMAR: Dynamic Multi-Anchor Retrieval with Structure-Aware Query Reformulation for Knowledge-Augmented Generation

Applied Sciences
Retrieval-Augmented Generation (RAG) has become an important paradigm for knowledge-intensive natural language processing, as it enables Large Language Models (LLMs) to access external evidence beyond their parametric memory.
Zhou Lei, Yanqi Xu, Shengbo Chen
doaj   +1 more source

Retrieval-Augmented Generation with Graphs (GraphRAG)

CoRR
Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected by edges" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in
Haoyu Han 0001, Yu Wang 0160, Harry Shomer, Kai Guo 0003, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A. Rossi, Subhabrata Mukherjee, Xianfeng Tang, Qi He 0002, Zhigang Hua, Bo Long, Tong Zhao 0003, Neil Shah, Amin Javari, Yinglong Xia, Jiliang Tang   +17 more
openaire   +2 more sources

Adaptive Multimodal Fusion Architecture for Heterogeneous Embedding Spaces in Retrieval-Augmented Generation Systems

IEEE Access
Retrieval-augmented generation systems integrate external information to mitigate hallucinations in large language models, yet existing multimodal retrieval-augmented generation implementations struggle with heterogeneous embedding spaces from diverse ...
Timothy Dillan, Sani Muhamad Isa, Abba Suganda Girsang, Derwin Suhartono   +3 more
doaj   +1 more source

Retrieval-Augmented Generation with Hierarchical Knowledge

Findings of the Association for Computational Linguistics: EMNLP 2025
EMNLP 2025 ...
Haoyu Huang, Yongfeng Huang, Junjie Yang, Zhenyu Pan, Yongqiang Chen 0002, Kaili Ma 0001, Hongzhi Chen, James Cheng   +7 more
openaire   +3 more sources

Bridging text and topology: empowering large language models through graph retrieval for constraint-aware reasoning in campus digital twins

International Journal of Digital Earth
Large language models (LLMs) have demonstrated remarkable capabilities in understanding and generating human language from heterogeneous data sources.
Wenyu Zhang, Suphanut Jamonnak, Weishan Bai, Xinyue Ye   +3 more
doaj   +1 more source

Loops On Retrieval Augmented Generation (LoRAG)

CoRR
This paper presents Loops On Retrieval Augmented Generation (LoRAG), a new framework designed to enhance the quality of retrieval-augmented text generation through the incorporation of an iterative loop mechanism. The architecture integrates a generative model, a retrieval mechanism, and a dynamic loop module, allowing for iterative refinement of the ...
Ayush Thakur, Rashmi Vashisth
openaire   +2 more sources

MGPRAG: Enhancing Medical Large Language Models via Precision Retrieval-Augmented Generation

IEEE Access
Large language models(LLMs) have demonstrated strong performance in general tasks, but remain insufficiently trusted in complex clinical question answering (CQA). This is largely due to concerns about the accuracy of the generated content.
Yanwen Shen, Dahong Xu, Xi Li, Lei Fu, Hong Liu   +4 more
doaj   +1 more source

Data Auctions for Retrieval Augmented Generation

CoRR
We study the problem of data selling for Retrieval Augmented Generation (RAG) tasks in Generative AI applications. We model each buyer's valuation of a dataset with a natural coverage-based valuation function that increases with the inclusion of more relevant data points that would enhance responses to anticipated queries.
Minbiao Han, Seyed A. Esmaeili, Michael Albert 0002, Haifeng Xu   +3 more
openaire   +2 more sources

Retrieval-Augmented Generation with Conflicting Evidence

CoRR
Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources while also suppressing inaccurate information from noisy or ...
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal   +3 more
openaire   +2 more sources

MEGA-RAG: a retrieval-augmented generation framework with multi-evidence guided answer refinement for mitigating hallucinations of LLMs in public health

Frontiers in Public Health
IntroductionThe increasing adoption of large language models (LLMs) in public health has raised significant concerns about hallucinations-factually inaccurate or misleading outputs that can compromise clinical communication and policy decisions.MethodsWe
Shan Xu, Shan Xu, Zhaokun Yan, Chengxiao Dai, Chengxiao Dai, Fan Wu   +5 more
doaj   +1 more source