{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:07:24Z","timestamp":1770062844731,"version":"3.49.0"},"reference-count":75,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T00:00:00Z","timestamp":1712966400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1016\/j.engappai.2024.108166","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T10:09:48Z","timestamp":1709201388000},"page":"108166","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":18,"special_numbering":"PB","title":["A comparative analysis of knowledge injection strategies for large language models in the scholarly domain"],"prefix":"10.1016","volume":"133","author":[{"given":"Andrea","family":"Cadeddu","sequence":"first","affiliation":[]},{"given":"Alessandro","family":"Chessa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-6992","authenticated-orcid":false,"given":"Vincenzo","family":"De Leo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4668-2476","authenticated-orcid":false,"given":"Gianni","family":"Fenu","sequence":"additional","affiliation":[]},{"given":"Enrico","family":"Motta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6557-3131","authenticated-orcid":false,"given":"Francesco","family":"Osborne","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-6183","authenticated-orcid":false,"given":"Diego","family":"Reforgiato Recupero","sequence":"additional","affiliation":[]},{"given":"Angelo","family":"Salatino","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4518-1429","authenticated-orcid":false,"given":"Luca","family":"Secchi","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2024.108166_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.simpa.2022.100444","article-title":"R-classify: Extracting research papers\u2019 relevant concepts from a controlled vocabulary","volume":"14","author":"Aggarwal","year":"2022","journal-title":"Softw. Impacts"},{"key":"10.1016\/j.engappai.2024.108166_b2","doi-asserted-by":"crossref","first-page":"32862","DOI":"10.1109\/ACCESS.2020.2973928","article-title":"Named entity extraction for knowledge graphs: A literature overview","volume":"8","author":"Al-Moslmi","year":"2020","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.engappai.2024.108166_b3","article-title":"Artificial hallucinations in ChatGPT: implications in scientific writing","volume":"15","author":"Alkaissi","year":"2023","journal-title":"Cureus"},{"key":"10.1016\/j.engappai.2024.108166_b4","series-title":"Neuro-symbolic visual reasoning: Disentangling \u201cvisual\u201d from \u201creasoning\u201d","author":"Amizadeh","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b5","series-title":"19th International Semantic Web Conference","article-title":"The AIDA dashboard: Analysing conferences with semantic technologies","author":"Angioni","year":"2020"},{"issue":"4","key":"10.1016\/j.engappai.2024.108166_b6","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1162\/qss_a_00162","article-title":"AIDA: A knowledge graph about research dynamics in academia and industry","volume":"2","author":"Angioni","year":"2021","journal-title":"Quant. Sci. Stud."},{"issue":"1","key":"10.1016\/j.engappai.2024.108166_b7","doi-asserted-by":"crossref","first-page":"7240","DOI":"10.1038\/s41598-023-33607-z","article-title":"The SciQA scientific question answering benchmark for scholarly knowledge","volume":"13","author":"Auer","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.engappai.2024.108166_b8","series-title":"Findings of the Association for Computational Linguistics","first-page":"1644","article-title":"TweetEval: Unified benchmark and comparative evaluation for tweet classification","author":"Barbieri","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b9","series-title":"International Workshop on Document Analysis Systems","first-page":"451","article-title":"From automatic keyword detection to ontology-based topic modeling","author":"Beck","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b10","series-title":"2019 IEEE 19th International Conference on Advanced Learning Technologies, vol. 2161","first-page":"42","article-title":"Semantic-enhanced recommendation of video lectures","author":"Borges","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b11","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"4762","article-title":"COMET: Commonsense transformers for automatic knowledge graph construction","author":"Bosselut","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b12","series-title":"HateBERT: Retraining BERT for abusive language detection in english","author":"Caselli","year":"2020"},{"issue":"4","key":"10.1016\/j.engappai.2024.108166_b13","doi-asserted-by":"crossref","DOI":"10.3390\/a16040196","article-title":"Attention-survival score: A metric to choose better keywords and improve visibility of information","volume":"16","author":"Chamorro-Padial","year":"2023","journal-title":"Algorithms"},{"issue":"Preprint","key":"10.1016\/j.engappai.2024.108166_b14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3233\/SW-233282","article-title":"Explanation Ontology: A general-purpose, semantic representation for supporting user-centered explanations","volume":"Preprint","author":"Chari","year":"2023","journal-title":"Semant Web"},{"key":"10.1016\/j.engappai.2024.108166_b15","series-title":"ADBIS, TPDL and EDA 2020 Common Workshops and Doctoral Consortium","first-page":"323","article-title":"Artsim: improved estimation of current impact for recent articles","author":"Chatzopoulos","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b16","doi-asserted-by":"crossref","first-page":"67567","DOI":"10.1109\/ACCESS.2023.3292153","article-title":"Data-driven methodology for knowledge graph generation within the tourism domain","volume":"11","author":"Chessa","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2024.108166_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109945","article-title":"SCICERO: A deep learning and NLP approach for generating scientific knowledge graphs in the computer science domain","volume":"258","author":"Dess\u00ed","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.engappai.2024.108166_b18","series-title":"The Semantic Web\u2013ISWC 2022: 21st International Semantic Web Conference, Virtual Event, October 23\u201327, 2022, Proceedings","first-page":"678","article-title":"CS-kg: A large-scale knowledge graph of research entities and claims in computer science","author":"Dess\u00ed","year":"2022"},{"key":"10.1016\/j.engappai.2024.108166_b19","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b20","series-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"Dodge","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b21","series-title":"Injecting domain knowledge in language models for task-oriented dialogue systems","author":"Emelin","year":"2022"},{"key":"10.1016\/j.engappai.2024.108166_b22","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.patrec.2021.10.004","article-title":"Semi-lexical languages: a formal basis for using domain knowledge to resolve ambiguities in deep-learning based computer vision","volume":"152","author":"Gangopadhyay","year":"2021","journal-title":"Pattern Recognit. Lett."},{"issue":"9","key":"10.1016\/j.engappai.2024.108166_b23","doi-asserted-by":"crossref","first-page":"3596","DOI":"10.1109\/JBHI.2021.3062322","article-title":"Limitations of transformers on clinical text classification","volume":"25","author":"Gao","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.engappai.2024.108166_b24","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4539","article-title":"On the use of context for predicting citation worthiness of sentences in scholarly articles","author":"Gosangi","year":"2021"},{"key":"10.1016\/j.engappai.2024.108166_b25","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"REALM: Retrieval-augmented language model pre-training","author":"Guu","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b26","series-title":"Incorporating knowledge resources into natural language processing techniques to advance academic research and application development","author":"Han","year":"2023"},{"issue":"2","key":"10.1016\/j.engappai.2024.108166_b27","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1145\/3397512","article-title":"A review of the semantic web field","volume":"64","author":"Hitzler","year":"2021","journal-title":"Commun. ACM"},{"key":"10.1016\/j.engappai.2024.108166_b28","series-title":"Contextualized representations using textual encyclopedic knowledge","author":"Joshi","year":"2021"},{"key":"10.1016\/j.engappai.2024.108166_b29","series-title":"AMMUS : A survey of transformer-based pretrained models in natural language processing","author":"Kalyan","year":"2021"},{"key":"10.1016\/j.engappai.2024.108166_b30","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","first-page":"6975","article-title":"SentiLARE: Sentiment-aware language representation learning with linguistic knowledge","author":"Ke","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b31","first-page":"1","article-title":"Research paper classification systems based on TF-IDF and LDA schemes","volume":"9","author":"Kim","year":"2019","journal-title":"Hum. Centr. Comput. Inf. Sci."},{"key":"10.1016\/j.engappai.2024.108166_b32","series-title":"Geotechnical Parrot Tales (GPT): Overcoming GPT hallucinations with prompt engineering for geotechnical applications","author":"Kumar","year":"2023"},{"key":"10.1016\/j.engappai.2024.108166_b33","doi-asserted-by":"crossref","first-page":"91802","DOI":"10.1109\/ACCESS.2022.3201542","article-title":"K-LM: knowledge augmenting in language models within the scholarly domain","volume":"10","author":"Kumar","year":"2022","journal-title":"IEEE Access"},{"issue":"2","key":"10.1016\/j.engappai.2024.108166_b34","article-title":"Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","year":"2023","journal-title":"PLoS Dig. Health"},{"key":"10.1016\/j.engappai.2024.108166_b35","series-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","author":"Lee","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b36","series-title":"A benchmark for lease contract review","author":"Leivaditi","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b37","series-title":"PyTorch-BigGraph: A large-scale graph embedding system","author":"Lerer","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b38","series-title":"Learning Technologies and Systems: 21st International Conference on Web-Based Learning, ICWL 2022, and 7th International Symposium on Emerging Technologies for Education, SETE 2022, Tenerife, Spain, November 21\u201323, 2022, Revised Selected Papers","first-page":"148","article-title":"Constructing low-redundant and high-accuracy knowledge graphs for education","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2024.108166_b39","first-page":"1","article-title":"Pre-train , prompt , and predict : A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.engappai.2024.108166_b40","series-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b41","series-title":"K-BERT: Enabling language representation with knowledge graph","author":"Liu","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b42","unstructured":"L\u00f6ffler, F., Wesp, V., Babalou, S., Kahn, P., Lachmann, R., Sateli, B., Witte, R., K\u00f6nig-Ries, B., 2020. ScholarLensViz: A Visualization Framework for Transparency in Semantic User Profiles. In: Taylor, K., Gon C\u00c7calves, R., Lecue, F., Yan, J. (Eds.), Proceedings of the ISWC 2020 Demos and Industry Tracks: From Novel Ideas to Industrial Practice Co-Located with 19th International Semantic Web Conference. ISWC 2020, Globally Online, November 1-6, 2020 UTC."},{"issue":"1","key":"10.1016\/j.engappai.2024.108166_b43","article-title":"Aggregate functions in categorical data skyline search (CDSS) for multi-keyword document search","volume":"9","author":"Mardiah","year":"2023","journal-title":"Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika"},{"key":"10.1016\/j.engappai.2024.108166_b44","doi-asserted-by":"crossref","first-page":"22468","DOI":"10.1109\/ACCESS.2023.3253388","article-title":"Integrating conversational agents and knowledge graphs within the scholarly domain","volume":"11","author":"Meloni","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2024.108166_b45","series-title":"Proceedings of the 7th International Conference on Semantic Systems","first-page":"1","article-title":"Dbpedia spotlight: Shedding light on the web of documents","author":"Mendes","year":"2011"},{"key":"10.1016\/j.engappai.2024.108166_b46","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1581","article-title":"SKILL: Structured knowledge infusion for large language models","author":"Moiseev","year":"2022"},{"key":"10.1016\/j.engappai.2024.108166_b47","series-title":"SKILL: structured knowledge infusion for large language models","author":"Moiseev","year":"2022"},{"key":"10.1016\/j.engappai.2024.108166_b48","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/j.neucom.2021.02.100","article-title":"Trans4E: Link prediction on scholarly knowledge graphs","volume":"461","author":"Nayyeri","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2024.108166_b49","series-title":"GPT-4 technical report","author":"OpenAI","year":"2023"},{"key":"10.1016\/j.engappai.2024.108166_b50","series-title":"The Semantic Web","first-page":"408","article-title":"Klink-2: Integrating multiple web sources to generate semantic topic networks","author":"Osborne","year":"2015"},{"key":"10.1016\/j.engappai.2024.108166_b51","series-title":"The Semantic Web","first-page":"460","article-title":"Exploring scholarly data with rexplore","author":"Osborne","year":"2013"},{"key":"10.1016\/j.engappai.2024.108166_b52","series-title":"Enriching BERT with knowledge graph embeddings for document classification","author":"Ostendorff","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b53","first-page":"1","article-title":"Knowledge graphs: opportunities and challenges","author":"Peng","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.engappai.2024.108166_b54","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"3350","article-title":"ERICA: Improving entity and relation understanding for pre-trained language models via contrastive learning","author":"Qin","year":"2021"},{"key":"10.1016\/j.engappai.2024.108166_b55","series-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","first-page":"3973","author":"Reimers","year":"2019"},{"issue":"1","key":"10.1016\/j.engappai.2024.108166_b56","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s13278-023-01085-w","article-title":"ACE 2.0: A comprehensive tool for automatic extraction, analysis, and digital profiling of the researchers in Scientific Communities","volume":"13","author":"Rizvi","year":"2023","journal-title":"Soc. Netw. Anal. Min."},{"key":"10.1016\/j.engappai.2024.108166_b57","series-title":"Representing scientific literature evolution via temporal knowledge graphs","author":"Rossanez","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b58","series-title":"Diversity of expertise is key to scientific impact: a large-scale analysis in the field of computer science","author":"Salatino","year":"2023"},{"key":"10.1016\/j.engappai.2024.108166_b59","series-title":"The Semantic Web","first-page":"507","article-title":"Improving editorial workflow and metadata quality at springer nature","author":"Salatino","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b60","series-title":"Proceedings of the 18th ACM\/IEEE on Joint Conference on Digital Libraries","first-page":"303","article-title":"AUGUR: Forecasting the emergence of new research topics","author":"Salatino","year":"2018"},{"key":"10.1016\/j.engappai.2024.108166_b61","first-page":"1","article-title":"CSO classifier 3.0: a scalable unsupervised method for classifying documents in terms of research topics","author":"Salatino","year":"2022","journal-title":"Int. J. Dig. Lib."},{"key":"10.1016\/j.engappai.2024.108166_b62","series-title":"Digital Libraries for Open Knowledge","first-page":"296","article-title":"The CSO classifier: Ontology-driven detection of research topics in scholarly articles","author":"Salatino","year":"2019"},{"key":"10.1016\/j.engappai.2024.108166_b63","series-title":"The Semantic Web","first-page":"187","article-title":"The computer science ontology: A large-scale taxonomy of research areas","author":"Salatino","year":"2018"},{"key":"10.1016\/j.engappai.2024.108166_b64","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.aiopen.2021.06.004","article-title":"CokeBERT: Contextual knowledge selection and embedding towards enhanced pre-trained language models","volume":"2","author":"Su","year":"2021","journal-title":"AI Open"},{"key":"10.1016\/j.engappai.2024.108166_b65","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"3660","article-title":"CoLAKE: Contextualized language and knowledge embedding","author":"Sun","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b66","series-title":"The Semantic Web","first-page":"341","article-title":"Ontology-based recommendation of editorial products","author":"Thanapalasingam","year":"2018"},{"key":"10.1016\/j.engappai.2024.108166_b67","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.engappai.2024.108166_b68","series-title":"Digital Libraries for Open Knowledge","first-page":"48","article-title":"VeTo: Expert set expansion in academia","author":"Vergoulis","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b69","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1162\/tacl_a_00360","article-title":"KEPLER: A unified model for knowledge embedding and pre-trained language representation","volume":"9","author":"Wang","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.engappai.2024.108166_b70","series-title":"K-adapter: Infusing knowledge into pre-trained models with adapters","author":"Wang","year":"2021"},{"key":"10.1016\/j.engappai.2024.108166_b71","series-title":"KILM: Knowledge injection into encoder-decoder language models","author":"Xu","year":"2023"},{"key":"10.1016\/j.engappai.2024.108166_b72","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","first-page":"6442","article-title":"LUKE: Deep contextualized entity representations with entity-aware self-attention","author":"Yamada","year":"2020"},{"key":"10.1016\/j.engappai.2024.108166_b73","series-title":"A survey of knowledge enhanced pre-trained models","first-page":"1","author":"Yang","year":"2021"},{"key":"10.1016\/j.engappai.2024.108166_b74","doi-asserted-by":"crossref","unstructured":"Zhang, X., Chandrasegaran, S., Ma, K.-L., 2021. ConceptScope: Organizing and Visualizing Knowledge in Documents based on Domain Ontology. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. pp. 1\u201313.","DOI":"10.1145\/3411764.3445396"},{"key":"10.1016\/j.engappai.2024.108166_b75","series-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","first-page":"1441","article-title":"ERNIE: Enhanced language representation with informative entities","author":"Zhang","year":"2019"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197624003245?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197624003245?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:54:00Z","timestamp":1717289640000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197624003245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":75,"alternative-id":["S0952197624003245"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2024.108166","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A comparative analysis of knowledge injection strategies for large language models in the scholarly domain","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2024.108166","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108166"}}