Results 51 to 60 of about 14,626 (158)

Using Retrieval vs. Cache Augmented Generation for a Pok´emon Chatbot

Proceedings of the International Florida Artificial Intelligence Research Society Conference
Cache Augmented Generation (CAG) can be an alternative to Retrieval Augmented Generation (RAG). There are differences between the two frameworks, but they work largely in the same way.
Cengiz Gunay, Jonathan Tran
doaj   +1 more source

Enhanced Retrieval-Augmented Generation Using Low-Rank Adaptation

Applied Sciences
Recent advancements in retrieval-augmented generation (RAG) have substantially enhanced the efficiency of information retrieval. However, traditional RAG-based systems still encounter challenges, such as high latency in output decision making, the ...
Yein Choi, Sungwoo Kim, Yipene Cedric Francois Bassole, Yunsick Sung   +3 more
doaj   +1 more source

Retrieval augmented generation with LLMs for enterprise proposal automation [PDF]

ITM Web of Conferences
Enterprise proposal writing as a response to RFPs is a very grave time-consuming undertaking since you must read and understand a stack of documentation correctly to ensure that everything is per the requirements.
S Bakiyalakshmi, C Sanjay, D Sriram
doaj   +1 more source

Multimodal retrieval-augmented generation framework for machine translation

ETRI Journal
The development of multimodal machine translation (MMT) systems has attracted significant interest due to their potential to enhance translation accuracy with visual information.
Shijian Li
doaj   +1 more source

DuetRAG: Collaborative Retrieval-Augmented Generation

CoRR
5 ...
Dian Jiao, Li Cai, Jingsheng Huang, Wenqiao Zhang, Siliang Tang, Yueting Zhuang   +5 more
openaire   +2 more sources

GraphTrace: A Modular Retrieval Framework Combining Knowledge Graphs and Large Language Models for Multi-Hop Question Answering

Computers
This paper introduces GraphTrace, a novel retrieval framework that integrates a domain-specific knowledge graph (KG) with a large language model (LLM) to improve information retrieval for complex, multi-hop queries.
Anna Osipjan, Hanieh Khorashadizadeh, Akasha-Leonie Kessel, Sven Groppe, Jinghua Groppe   +4 more
doaj   +1 more source

Question Decomposition for Retrieval-Augmented Generation

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Grounding large language models (LLMs) in verifiable external sources is a well-established strategy for generating reliable answers. Retrieval-augmented generation (RAG) is one such approach, particularly effective for tasks like question answering: it retrieves passages that are semantically related to the question and then conditions the model on ...
Paul J. L. Ammann, Jonas Golde, Alan Akbik   +2 more
openaire   +2 more sources

FictionRAG: A Stateful Metacognitive Framework for High-Fidelity Long-Narrative Role-Playing

Algorithms
Maintaining high-fidelity character personas and tracking trusted narrative facts remain significant challenges for LLM-based role-playing systems, particularly in long-context scenarios. Traditional Retrieval-Augmented Generation (RAG) approaches, which
Yifei Deng, Yudong Zhang, Jingpu Yang, Miao Fang   +3 more
doaj   +1 more source

Retrieval-augmented generation in multilingual settings

Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024)
Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e.
Nadezhda Chirkova, David Rau, Hervé Déjean, Thibault Formal, Stéphane Clinchant, Vassilina Nikoulina   +5 more
openaire   +2 more sources

KAQG: A Knowledge-Graph-Enhanced RAG for Difficulty-Controlled Question Generation

IEEE Access
This study introduces Knowledge Augmented Question Generation (KAQG), an educational assessment framework that integrates Item Response Theory (IRT), Bloom’s Taxonomy, and knowledge graphs into a multi-agent Retrieval-Augmented Generation (RAG ...
Ching Han Chen, Ming Fang Shiu
doaj   +1 more source