Results 11 to 20 of about 14,626 (158)

Hallucination Mitigation for Retrieval-Augmented Large Language Models: A Review

Mathematics
Retrieval-augmented generation (RAG) leverages the strengths of information retrieval and generative models to enhance the handling of real-time and domain-specific knowledge.
Wan Zhang, Jing Zhang
doaj   +1 more source

Chain-of-Retrieval Augmented Generation

CoRR
Accepted by NeurIPS ...
Liang Wang 0046, Haonan Chen 0005, Nan Yang 0002, Xiaolong Huang, Zhicheng Dou, Furu Wei   +5 more
openaire   +2 more sources

Leveraging Retrieval-Augmented Generation for Swahili Language Conversation Systems

Applied Sciences
A conversational system is an artificial intelligence application designed to interact with users in natural language, providing accurate and contextually relevant responses.
Edmund V. Ndimbo, Qin Luo, Gimo C. Fernando, Xu Yang, Bang Wang   +4 more
doaj   +1 more source

Distributed Retrieval-Augmented Generation

CoRR
As large language models (LLMs) become increasingly adopted on edge devices, Retrieval-Augmented Generation (RAG) is gaining prominence as a solution to address factual deficiencies and hallucinations by integrating external knowledge. However, centralized RAG architectures face significant challenges in data privacy and scalability.
Chenhao Xu 0003, Longxiang Gao, Yuan Miao, Xi Zheng 0001   +3 more
openaire   +2 more sources

Tracert-Retrieval-Augmented Generation: Boosting Multi-Hop Retrieval-Augmented Generation with Direction-Aware Graph Traversal

Engineering Proceedings
Tracert-retrieval-augmented generation (RAG) is a novel retrieval-augmented framework designed for efficient, document-level multi-hop reasoning. Unlike conventional RAG systems that retrieve top-k text segments based solely on dense similarity, Tracert ...
Siu-Him Zhang, Jhe-Wei Lin
doaj   +1 more source

Review of Document Q&A Driven by Multimodal Retrieval-Augmented Generation (Invited) [PDF]

Jisuanji gongcheng
Traditional Retrieval-Augmented Generation (RAG) methods predominantly focus on pure-text scenarios. In these scenarios, their retrieval and generation mechanisms encounter difficulties in effectively modeling common visual elements, spatial layouts, and
LI Zeming, WANG Shuliang, SHANG Zihe, SHENG Ming
doaj   +1 more source

Parametric Retrieval Augmented Generation

Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval
Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In particular, existing RAG methods append relevant documents retrieved from external corpus or databases to the input of ...
Weihang Su, Yichen Tang 0001, Qingyao Ai, Junxi Yan, Changyue Wang 0001, Hongning Wang, Ziyi Ye, Yujia Zhou 0002, Yiqun Liu 0001   +8 more
openaire   +2 more sources

Next Sentence Prediction with BERT as a Dynamic Chunking Mechanism for Retrieval-Augmented Generation Systems

Proceedings of the International Florida Artificial Intelligence Research Society Conference
Retrieval-Augmented Generation systems enhance the generative capabilities of large language models by grounding their responses in external knowledge bases, addressing some of their major limitations and improving their reliability for tasks requiring ...
Alexandre Thurow Bender, Gabriel Almeida Gomes, Ulisses Brisolara Corrêa, Ricardo Matsumura Araujo   +3 more
doaj   +1 more source

Accelerating Retrieval-Augmented Generation

Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1
An evolving solution to address hallucination and enhance accuracy in large language models (LLMs) is Retrieval-Augmented Generation (RAG), which involves augmenting LLMs with information retrieved from an external knowledge source, such as the web. This paper profiles several RAG execution pipelines and demystifies the complex interplay between their ...
Derrick Quinn, Mohammad Nouri, Neel Patel, John Salihu, Alireza Salemi, Sukhan Lee 0002, Hamed Zamani, Mohammad Alian   +7 more
openaire   +2 more sources

Artificial intelligence-driven clinical guideline recommendations in maternal care: How trustworthy are they?

Biomédica: revista del Instituto Nacional de Salud
Introduction. Medical staff often face difficulties in consulting and applying clinical guidelines in practice. Large language models, especially when combined with retrieval-augmented generation, may help overcome these challenges by producing context ...
Jairo J. Pérez, Andrés F. Giraldo-Forero, Santiago Rúa, Daniel Betancur, Zuliany Urquina, Pablo Castañeda, Sara Arango-Valencia, Juan Guillermo Barrientos-Gómez, Ever A. Torres-Silva, Andrés Orozco-Duque   +9 more
doaj   +1 more source