Results 131 to 140 of about 36,775 (295)

Dynamic Retrieval-Augmented Generation

Current state-of-the-art large language models are effective in generating high-quality text and encapsulating a broad spectrum of world knowledge. These models, however, often hallucinate and lack locally relevant factual data.
Litvinov, Denis, Galimzyanov, Timur, Zharov, Yaroslav, Shapkin, Anton, Bogomolov, Egor, Bryksin, Timofey   +5 more
core  

Retrieval-Augmented Multi-Floor Building Image Generation [PDF]

Demand for generating building images from text prompts grows, despite recent advances in diffusion models greatly enhancing image quality. The current generative models struggle with controlling the number of floors.
Jin, Hao, Xie, Haoran, Wang, Zhengyang
core  

Benchmarking Large Language Models in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is a promising approach for mitigating the hallucination of large language models (LLMs). However, existing research lacks rigorous evaluation of the impact of retrieval-augmented generation on different large ...
Lin, Hongyu, Chen, Jiawei, Sun, Le, Han, Xianpei   +3 more
core   +1 more source

Palmitic Acid Promotes Antiviral Innate Immunity via ZDHHC20‐Mediated CMPK2 Palmitoylation

Advanced Science, EarlyView.
Metabolites have important functions in innate immune activation and regulation. Wang et al. uncover metabolic regulation of antiviral immunity through CMPK2 palmitoylation, which regulates CMPK2 mitochondrial localization and is promoted by ZDHHC20 but reversed by PPT1, inhibition of which antagonizes viral infection in mice.
Yujia Wang, Zenghui Cui, Yunkai Zhang, Zhiqing Li, Xuetao Cao   +4 more
wiley   +1 more source

Differentially Private Retrieval-Augmented Generation

CoRR
Retrieval-augmented generation (RAG) is a widely used framework for reducing hallucinations in large language models (LLMs) on domain-specific tasks by retrieving relevant documents from a database to support accurate responses. However, when the database contains sensitive corpora, such as medical records or legal documents, RAG poses serious privacy ...
Tingting Tang, James Flemings, Yongqin Wang, Murali Annavaram   +3 more
openaire   +2 more sources

RGAR:Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering [PDF]

Medical question answering fundamentally relies on accurate clinical knowledge. The dominant paradigm, Retrieval-Augmented Generation (RAG), acquires expertise conceptual knowledge from large-scale medical corpus to guide general-purpose large language ...
Wang, Wenwen, Liang, Sichu, Zhou, Deyu, Zhu, Hongyu, He, Yulan, Zhang, Linhai   +5 more
core   +1 more source

Fosl2 Regulates FSH‐Dependent Follicle Maturation Through Feedback Amplification of FSH/FSHR Signaling

Advanced Science, EarlyView.
This study identifies a FOSL2‐driven positive feedback loop that amplifies FSH/FSHR signaling. During FSH‐dependent follicle maturation, FSH induces Fosl2 expression via the cAMP‐PKA‐CREB cascade. FOSL2 in turn binds the promoters of Fshr and estrogen‐biosynthesis genes to enhance their transcription, thereby increasing Fshr mRNA level and amplifying ...
Hongru Shi, Chaoli Chen, Zaohong Ran, Jianning Liao, Zian Wu, Xiaodong Wang, Yongheng Zhao, Wenkai Ke, Bowen Tan, Yun Liu, Youqiang Su, Wei Ren, Xiang Li, Changjiu He   +13 more
wiley   +1 more source

Retrieval augmented generation for building datasets from scientific literature

JPhys Materials
In this work, we show that employing retrieval augmented generation (RAG) with a large language model (LLM) enables us to extract accurate data from scientific literature and construct datasets.
Piyush Ranjan Maharana, Ashwini Verma, Kavita Joshi   +2 more
doaj   +1 more source

A Survey of Multimodal Retrieval-Augmented Generation

CoRR
Multimodal Retrieval-Augmented Generation (MRAG) enhances large language models (LLMs) by integrating multimodal data (text, images, videos) into retrieval and generation processes, overcoming the limitations of text-only Retrieval-Augmented Generation (RAG). While RAG improves response accuracy by incorporating external textual knowledge, MRAG extends
Lang Mei, Siyu Mo, Zhihan Yang, Chong Chen 0001   +3 more
openaire   +2 more sources

RAGG: Retrieval-Augmented Grasp Generation Model

Intent-based grasp generation inherently involves challenges such as manipulation ambiguity and modality gaps. To address these, we propose a novel Retrieval-Augmented Grasp Generation model (RAGG).
Tang, Zhenhua, Hong, Richang, Ngo, Chong-Wah, Zhu, Bin, Hao, Yanbin   +4 more
core   +1 more source