A Survey of Knowledge Enhanced Pre-trained Language Models
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · 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) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“Secondly, considering the existing data is mainly the result of the interaction between multiple latent factors, distributed vectors can represent different impact factors by designing a specific network structure.”
BackgroundDeep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Inductive Representation Learning on Large Graphs
Hamilton, W. L., Ying, R., & Leskovec, J. (2017) · arXiv · doi:10.48550/arxiv.1706.02216 · Cited by 10,639
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 1×
“Besides, GloVe [74] computes word-word cooccurrence statistics from a large corpus as a supervised signal, and FastText [8] trains the model with text classification data.”
MethodA revision of bloom's taxonomy: an overview
Krathwohl, D. R. (2002) · Theory Into Practice · doi:10.1207/s15430421tip4104_2 · Cited by 8,132
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208
Modeling Relational Data with Graph Convolutional Networks
Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93417-4_38 · Cited by 5,570
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100 · cited 1×
“Around the same time, the introduction of ULMFiT offered valuable insights into multi-stage transfer and the fine-tuning of models [34].”
BackgroundKnowledge Graph Embedding by Translating on Hyperplanes
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8870 · Cited by 3,915 · cited 1×
“To tackle this problem of insufficiency of a single space for both entities and relations, TransH and TransR allows an entity to have distinct representations when involved in different relations [37, 110].”
BackgroundLearning Entity and Relation Embeddings for Knowledge Graph Completion
Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9491 · Cited by 3,749 · cited 1×
“TransD argues that entities serve as different types even with the same relations and construct dynamic mapping matrices by considering the interactions between entities and relations [55] .”
BackgroundA Survey on Knowledge Graphs: Representation, Acquisition, and Applications
Ji, S., Pan, S., Cambria, E., Marttinen, P., & Yu, P. S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3070843 · Cited by 2,947
Convolutional 2D Knowledge Graph Embeddings
Dettmers, T., Minervini, P., Stenetorp, P., & Riedel, S. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11573 · Cited by 2,486
Embedding Entities and Relations for Learning and Inference in Knowledge Bases
Yang, B., Yih, W.-T., He, X., Gao, J., & Deng, L. (2014) · arXiv · doi:10.48550/arxiv.1412.6575 · Cited by 2,252 · cited 2×
“…are symbols representing objects, relations, and functions, among which the objects refer to the individual or category of things, the relationships refer to the mapping between things, and the functions require the object in each domain to have a mapping value as a special form of a predicate.”
BackgroundMethodNatural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D. S., & Zettlemoyer, L. (2017) · arXiv · doi:10.48550/arxiv.1705.03551 · Cited by 1,650
Pre-trained models for natural language processing: A survey
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591 · cited 1×
“For more details of models, we refer readers to [57, 80].”
MethodA primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552 · cited 1×
“Much effort has been devoted to examining the knowledge encoded in PLMs by different probing ways [86].”
BackgroundERNIE: Enhanced Language Representation with Informative Entities
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., & Liu, Q. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1139 · Cited by 1,482 · cited 5×
“Then the tokens in text and entities will be aligned to combine the corresponding embedding of them by attention mechanism or other weighting operations [76, 120].”
BackgroundMethodInfluentialKiros, R., Zhu, Y., Salakhutdinov, R., Zemel, R. S., Torralba, A., Urtasun, R., & Fidler, S. (2015) · arXiv · doi:10.48550/arxiv.1506.06726 · Cited by 1,293 · cited 1×
“Following autoencoder-based neural models, pre-trained language models design specific neural networks to encode input data while using pre-trained tasks to decode learned representations.”
Method(2019) · doi:10.18653/v1/p19-1356 · Cited by 1,291 · cited 1×
“The objectives are to offer guidelines for users and researchers by comparing their pros and cons.”
BackgroundHierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., & Choi, Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1470 · Cited by 904 · cited 2×
“For instance, by transferring implicit knowledge from deep pre-trained language models, COMET learns to produce new objects coherent to its subject and relation and achieves Fig.”
BackgroundK-BERT: Enabling Language Representation with Knowledge Graph
Liu, W., Zhou, P., Zhao, Z., Wang, Z., Ju, Q., Deng, H., & Wang, P. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i03.5681 · Cited by 894 · cited 4×
“In addition, it is practical to ingest knowledge1 into a pre-trained checkpoint without training from scratch for a specific downstream application [58, 64].”
BackgroundMethodInfluentialLatent retrieval for weakly supervised open domain question answering
Lee, K., Chang, M.-W., & Toutanova, K. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1612 · Cited by 771
ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding
Sun, Y., Wang, S., Li, Y., Feng, S., Tian, H., Wu, H., & Wang, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6428 · Cited by 766
End-to-End Structure-Aware Convolutional Networks for Knowledge Base Completion
Shang, C., Tang, Y., Huang, J., Bi, J., He, X., & Zhou, B. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013060 · Cited by 725
(1993) · doi:10.1609/aimag.v14i1.1029 · Cited by 721
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
Wang, X., Gao, T., Zhu, Z., Zhang, Z., Liu, Z., Li, J., & Tang, J. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00360 · Cited by 676 · cited 2×
“To solve this problem, some KEPLMs generate the initial embedding of nodes with their contexts [62, 109].”
BackgroundMethodKnowledge Enhanced Contextual Word Representations
Peters, M. E., Neumann, M., Logan, R., Schwartz, R., Joshi, V., Singh, S., & Smith, N. A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1005 · Cited by 661 · cited 4×
“The line thickness of the graph represents the quantity of each type.”
BackgroundInfluential(2019) · doi:10.18653/v1/n19-1419 · Cited by 601
Composition-based Multi-Relational Graph Convolutional Networks
Vashishth, S., Sanyal, S., Nitin, V., & Talukdar, P. (2019) · arXiv · doi:10.48550/arxiv.1911.03082 · Cited by 581 · cited 1×
“For the sake of obtaining models with reasoning capabilities, researchers adopt the term ontology to describe what can be computationally represented of the world in a program.”
MethodHolographic embeddings of knowledge graphs
Nickel, M., Rosasco, L., & Poggio, T. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10314 · Cited by 559
Zero-Shot Relation Extraction via Reading Comprehension
Levy, O., Seo, M., Choi, E., & Zettlemoyer, L. (2017) · Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) · doi:10.18653/v1/k17-1034 · Cited by 482 · cited 1×
“Conversely, word-level linguistic knowledge is centered around individual words, capturing specific attributes such as part-of-speech tags and sentiment polarity.”
BackgroundPTR: Prompt Tuning with Rules for Text Classification
Han, X., Zhao, W., Ding, N., Liu, Z., & Sun, M. (2021) · arXiv · doi:10.48550/arxiv.2105.11259 · Cited by 478 · cited 4×
“By integrating symbol reasoning system into the learning pipeline, knowledge form unchanged KEPLMs reconcile the advantages of effective perception of PLMs and reasoning and interpretability of symbolic representation [29].”
BackgroundMethodInfluentialSearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
Dunn, M., Sagun, L., Higgins, M., Guney, V. U., Cirik, V., & Cho, K. (2017) · arXiv · doi:10.48550/arxiv.1704.05179 · Cited by 359
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Marcus, G. (2020) · arXiv · doi:10.48550/arxiv.2002.06177 · Cited by 297 · cited 1×
“In the words of Marcus: intelligence can be counted on to apply what it knows to a wide range of problems systematically and reliably, synthesizing knowledge from a variety of sources such that it can reason flexibly and dynamically about the world, transferring what it learns in one context to another, in the way tha…”
BackgroundCommonGen: A constrained text generation challenge for generative commonsense reasoning
Lin, B. Y., Zhou, W., Shen, M., Zhou, P., Bhagavatula, C., Choi, Y., & Ren, X. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.165 · Cited by 239 · cited 1×
“As we observe, PLMs lack commonsense knowledge and generate illogical sentences [54].”
BackgroundCoLAKE: Contextualized Language and Knowledge Embedding
Sun, T., Shao, Y., Qiu, X., Guo, Q., Hu, Y., Huang, X., & Zhang, Z. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.327 · Cited by 185
Barack’s Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling
Logan, R., Liu, N. F., Peters, M. E., Gardner, M., & Singh, S. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1598 · Cited by 168 · cited 1×
“Contextual triplets can provide critical entity knowledge for PLMs, particularly in instances where these models struggle to infer entity semantics only from context.”
BackgroundExploiting Structured Knowledge in Text via Graph-Guided Representation Learning
Shen, T., Mao, Y., He, P., Long, G., Trischler, A., & Chen, W. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.722 · Cited by 63
Faithful Embeddings for Knowledge Base Queries
Sun, H., Arnold, A. O., Bedrax-Weiss, T., Pereira, F., & Cohen, W. W. (2020) · arXiv · doi:10.48550/arxiv.2004.03658 · Cited by 51
SciBERT: A Pretrained Language Model for Scientific Text
Beltagy, I., Lo, K., & Cohan, A. (2019) · arXiv · doi:10.48550/arxiv.1903.10676 · Cited by 41
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases
Cao, B., Lin, H., Han, X., Sun, L., Yan, L., Liao, M., Xue, T., & Xu, J. (2021) · arXiv · doi:10.48550/arxiv.2106.09231 · Cited by 10
Cited by
Security and Privacy Challenges of Large Language Models: A Survey
Das, B. C., Amini, M. H., & Wu, Y. (2025) · ACM Computing Surveys · doi:10.1145/3712001 · Cited by 445
Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities
Ferrag, M. A., Alwahedi, F., Battah, A., Cherif, B., Mechri, A., Tihanyi, N., Bisztray, T., & Debbah, M. (2025) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2025.01.001 · Cited by 148
He, K., Mao, R., Lin, Q., Ruan, Y., Lan, X., Feng, M., & Cambria, E. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102963 · Cited by 147
Metadata
- Authors
- Yang, J., Hu, X., Xiao, G., & Shen, Y.
- Venue
- ACM Transactions on Asian and Low-Resource Language Information Processing
- Published
- 2024-03
- ISSN
- 2375-4699 (ISSN-L)
- 2375-4702
- OpenAlex
- W4392357044
- Cited by
- 47
- References
- 53
- FWCI
- 6.85
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.