WikiEvents - A Novel Resource for NLP Downstream Tasks
Abstract: Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs’ intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.
Show BibTeX
@inproceedings{DBLP:conf/esws/MichaelisHU23,
author = {Lars Michaelis and
Junbo Huang and
Ricardo Usbeck},
editor = {Mehwish Alam and
C{\'{a}}ssia Trojahn and
Sven Hertling and
Catia Pesquita and
Christian Aebeloe and
Hidir Aras and
Amr Azzam and
Juan Cano and
John Domingue and
Simon Gottschalk and
Olaf Hartig and
Katja Hose and
Sabrina Kirrane and
Pasquale Lisena and
Francesco Osborne and
Philipp D. Rohde and
Luc Steels and
Ruben Taelman and
Aisling Third and
Ilaria Tiddi and
Rima T{\"{u}}rker},
title = {WikiEvents - {A} Novel Resource for {NLP} Downstream Tasks},
booktitle = {Joint Proceedings of the {ESWC} 2023 Workshops and Tutorials co-located
with 20th European Semantic Web Conference {(ESWC} 2023), Hersonissos,
Greece, May 28-29, 2023},
series = {{CEUR} Workshop Proceedings},
volume = {3443},
publisher = {CEUR-WS.org},
year = {2023},
url = {https://ceur-ws.org/Vol-3443/ESWC\_2023\_SEMMES\_WikiEvents.pdf},
timestamp = {Thu, 27 Jul 2023 16:41:00 +0200},
biburl = {https://dblp.org/rec/conf/esws/MichaelisHU23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}