Results 21 to 30 of about 3,238,639 (146)

Swamped with Too Many Articles? GraphRAG Makes Getting Started Easy

AI
Background: Both early researchers, such as new graduate students, and experienced researchers face the challenge of sifting through vast amounts of literature to find their needle in a haystack.
Joëd Ngangmeni, Danda B. Rawat
doaj   +1 more source

DuetRAG: Collaborative Retrieval-Augmented Generation [PDF]

Retrieval-Augmented Generation (RAG) methods augment the input of Large Language Models (LLMs) with relevant retrieved passages, reducing factual errors in knowledge-intensive tasks.
Zhuang, Yueting, Zhang, Wenqiao, Tang, Siliang, Huang, Jingsheng, Jiao, Dian, Cai, Li   +5 more
core   +1 more source

Implementing Retrieval-Augmented Generation for Academic Libraries

International Journal of Librarianship
This article details the technical development of a Retrieval-Augmented Generation (RAG) system designed to enhance discovery within an academic library's institutional repository.
Wei Xuan
doaj   +1 more source

Corrective Retrieval Augmented Generation [PDF]

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,
Ling, Zhen-Hua, Zhu, Yun, Gu, Jia-Chen, Yan, Shi-Qi   +3 more
core   +1 more source

Data Imputation Based on Retrieval-Augmented Generation

Applied Sciences
Modern organizations collect increasing volumes of data to drive decision-making, often stored in centralized repositories such as data lakes, which consist of diverse structured and unstructured datasets.
Xiaojun Shi, Jiacheng Wang, Gregorius Justin Chung, Derick Julian, Lianpeng Qiao   +4 more
doaj   +1 more source

Biomedical retrieval-augmented generation for relation classification

Frontiers in Research Metrics and Analytics
The rapid expansion of biomedical literature requires automated methods for accurate and efficient information extraction. This study addresses relation classification: given a pair of annotated biomedical entities in a research article title and ...
Jannat, Charlie Dil, Tom Arodz, Bridget T. McInnes   +3 more
doaj   +1 more source

Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI) [PDF]

BackgroundOntologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form.
Ruemping, Troy, Wood, V., Dooley, Damion M, Reiser, L., Diehl, Alexander, Aleix Puig-Barbe, Reese, Justin P, O‘Neil, S., Weber, Magalie, Reese, Justin T, Leonore Reiser, Ray Stefancsik, Dooley, Damion, Harris, Nomi L, Reese, J. T., Marcin P. Joachimiak, Diehl, A. D., Haendel, M. A., Shawn O‘Neil, Duncan, W. D., Tiago Lubiana, Cameron, R., Mungall, C. J., Sid, Eric, Troy Ruemping, Leila Kiani, Bello, S. M., Gaudet, P., Kiani, L., Reese, Justin, Christopher J. Mungall, Magalie Weber, Eric Sid, Robb, Sofia, Kai Blumberg, Cameron, Rhiannon, Stefancsik, Ray, Anagnostopoulos, A. V., Osumi-Sutherland, D., Robb, Sofia MC, Valerie Wood, Dooley, D. M., Bello, Susan M, Puig, Aleix, Ruemping, T., Anagnostopoulos, Anna V, Anagnostopoulos, Anna, Anna V. Anagnostopoulos, Fey, Petra, Rhiannon Cameron, Bello, Susan, Sabrina Toro, Mungall, Christopher, Justin T. Reese, Sofia MC. Robb, Lubiana, T., Robb, Sofia Mc., Leigh Carmody, Blumberg, Kai, Joachimiak, Marcin, Osumi-Sutherland, David, Munoz-Torres, M. C., Puig-Barbe, Aleix, Wood, Valerie, Pascale Gaudet, Nomi L. Harris, Carmody, Leigh, Lubiana, Tiago, Toro, S., David Osumi-Sutherland, Seager, J., Duncan, William D, Toro, Sabrina, Diehl, Alexander D, Haendel, Melissa A, Seager, James, Petra Fey, Munoz-Torres, Monica C, Monica C. Munoz-Torres, Haendel, Melissa, Weber, M., Munoz-Torres, Monica, Blumberg, K., Joachimiak, M. P., Alexander D. Diehl, O‘Neil, Shawn, Robb, S. M., Damion M. Dooley, Fey, P., Sid, E., O\u27Neil, Shawn, James Seager, Melissa A. Haendel, Reiser, Leonore, Harris, Nomi, Kiani, Leila, William D. Duncan, Susan M. Bello, Stefancsik, R., Duncan, William, Harris, N. L., Bello, Sue, Joachimiak, Marcin P, Puig-Barbe, A., Gaudet, Pascale, Mungall, Christopher J, Carmody, L.   +106 more
core   +1 more source

Hybrid retrieval generation for structured reasoning with large language models

Discover Artificial Intelligence
Large Language Models (LLMs) exhibit strong generative capabilities but remain limited in structured knowledge domains due to factual inconsistency, shallow multi-hop reasoning, and weak alignment with domain constraints.
Rathinasamy Muthusami, Kandhasamy Saritha   +1 more
doaj   +1 more source

Advancing Retrosynthesis with Retrieval-Augmented Graph Generation

Diffusion-based molecular graph generative models have achieved significant success in template-free, single-step retrosynthesis prediction. However, these models typically generate reactants from scratch, often overlooking the fact that the scaffold of ...
Rao, J, Wang, Z, Wang, Zhen, Qiao, A, Yang, Y, Qiao, Anjie, Rao, Jiahua, Yang, Yuedong, Wei, Z, Wei, Zhewei   +9 more
core   +1 more source

Improving negative rejection ability in language models: A review of fine-tuned LLMs, RAG, and RAFT

Journal of King Saud University: Computer and Information Sciences
Large Language Models (LLMs) excel in text understanding and generation but struggle to reject irrelevant, ambiguous, or misleading queries, termed negative rejection, impacting reliability in high-stakes contexts.
Li Bowen, Zhong Zhuoqing, Zhang Hengyu, Sun Xubin, Baha Ihnaini   +4 more
doaj   +1 more source