A comparative analysis of knowledge injection strategies for large language models in the scholarly domain
Authors:
- Andrea CadedduACAndrea Cadeddu
- Alessandro ChessaACAlessandro Chessa
- Vincenzo De LeoVLVincenzo De Leo
- Gianni FenuGFGianni Fenu
- Enrico MottaEMEnrico Motta
- Francesco OsborneFOFrancesco Osborne
- Diego Reforgiato RecuperoDiego Reforgiato Recupero
- Angelo SalatinoASAngelo Salatino
- Luca SecchiLSLuca Secchi
Open Access
- 29 February 2024
- journal article
- research article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 133
Abstract
No abstract availableKeywords
This publication has 18 references indexed in Scilit:
- ACE 2.0: A Comprehensive tool for automatic extraction, analysis, and digital profiling of the researchers in Scientific CommunitiesSocial Network Analysis and Mining, 2023
- The SciQA Scientific Question Answering Benchmark for Scholarly KnowledgeScientific Reports, 2023
- Integrating Conversational Agents and Knowledge Graphs Within the Scholarly DomainIEEE Access, 2023
- R-classify: Extracting research papers’ relevant concepts from a controlled vocabularySoftware Impacts, 2022
- SCICERO: A deep learning and NLP approach for generating scientific knowledge graphs in the computer science domainKnowledge-Based Systems, 2022
- K-LM: Knowledge Augmenting in Language Models Within the Scholarly DomainIEEE Access, 2022
- Semi-lexical languages: a formal basis for using domain knowledge to resolve ambiguities in deep-learning based computer visionPattern Recognition Letters, 2021
- Trans4E: Link prediction on scholarly knowledge graphsNeurocomputing, 2021
- CokeBERT: Contextual knowledge selection and embedding towards enhanced pre-trained language modelsAI Open, 2021
- Named Entity Extraction for Knowledge Graphs: A Literature OverviewIEEE Access, 2020