Knowledge Base Construction from Pre-Trained Language Models

Workshop @ 22nd International Semantic Web Conference (ISWC 2023)

Language models such as chatGPT, BERT, and T5, have demonstrated remarkable outcomes in numerous AI applications. Research has shown that these models implicitly capture vast amounts of factual knowledge within their parameters, resulting in a remarkable performance in knowledge-intensive applications. The seminal paper "Language Models as Knowledge Bases?" sparked interest in the spectrum between language models (LMs) and knowledge graphs (KGs), leading to a diverse range of research on the usage of LMs for knowledge base construction, including (i) utilizing pre-trained LMs for knowledge base completion and construction tasks, (ii) performing information extraction tasks, like entity linking and relation extraction, and (iii) utilizing KGs to support LM based applications.

The 1st Workshop on Knowledge Base Construction from Pre-Trained Language Models (KBC-LM) workshop aims to give space to the emerging academic community that investigates these topics, host extended discussions around the LM-KBC Semantic Web challenge, and enable an informal exchange of researchers and practitioners.

Important Dates

Papers due: July 31, 2023
Notification to authors: August 31, 2023
Camera-ready deadline: September 14, 2023
Workshop dates: 6 November 2023


We invite contributions on the following topics:

  • Entity recognition and disambiguation with LMs
  • Relation extraction with LMs
  • Zero-shot and few-shot knowledge extraction from LMs
  • Consistency of LMs
  • Knowledge consolidation with LMs
  • Comparisons of LMs for KBC tasks
  • Methodological contributions on training and fine-tuning LMs for KBC tasks
  • Evaluations of downstream capabilities of LM-based KGs in tasks like QA
  • Designing robust prompts for large language model probing

Submissions can be novel research contributions or already published papers (these will be presentation-only, and not part of the workshop proceedings). Novel research papers can be either full papers (ca. 8-12 pages), or short papers presenting smaller or preliminary results (typically 3-6 pages). We are accepting demo and position papers as well. Check out also the LM-KBC challenge for further options to contribute to the workshop.

Submission and Review Process

Papers will be peer-reviewed by at least three researchers using a single-blind review. Accepted papers will be published on CEUR (unless authors opt out). Submissions need to be formatted according to the CEUR workshop proceedings (template). Papers can be submitted directly via Openreview.

Robert Bosch GmbH has signaled that they would likely sponsor a best paper award over 500 Euro.


10:00-10:10 Welcome
10:10-10:55 Keynote 1: Fabio Petroni [pdf]
10:55-11:15 Coffee break
11:15-12:35 1st Paper session (4 papers)
12:35-13:50 Lunch break
13:50-14:35 Keynote 2: Nora Kassner [pdf]
14:35-15:15 LM-KBC challenge winner talks
15:15-15:40 LM-KBC challenge poster session
15:40-16:10 Coffee break
16:10-17:10 2nd Paper session (3 papers)
17:10-17:40 Invited Talk: Mehdi Rezagholizadeh & Xiao Bo
17:40-17:50 Awards & closing session

1st Paper Session

  • [pdf] Language Models as Knowledge Bases for Visual Word Sense Disambiguation. Anastasia Kritharoula, Maria Lymperaiou, Giorgos Stamou
  • [pdf] Extracting Geographic Knowledge from Large Language Models: An Experiment. Konstantinos Salmas, Despina Athanasia Pantazi, Manolis Koubarakis
  • [pdf] Cross-validation of Answers with SUMO and GPT. Dan Lupu, Adrian Groza, Adam Pease
  • [pdf] Do Instruction-tuned Large Language Models Help with Relation Extraction?. Xue Li, Fina Polat, Paul Groth

2nd Paper Session

  • [pdf] Can large language models generate salient negative statements?. Hiba Arnaout, Simon Razniewski
  • [pdf] Towards Ontology Construction with Language Models. Maurice Funk, Simon Hosemann, Jean Christoph Jung, Carsten Lutz
  • [pdf] Towards syntax-aware pretraining and prompt engineering for knowledge retrieval from large language models. Stefan Dietze, Hajira Jabeen, Laura Kallmeyer, Stephan Linzbach

Challenge Posters

  • [pdf] (Track 1 Winner) Expanding the Vocabulary of BERT for Knowledge Base Construction*. Dong Yang, XU Wang, Remzi Celebi
  • [pdf] (Track 2 Winner) Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata*. Bohui Zhang, Ioannis Reklos, Nitisha Jain, Albert Meroño-Peñuela, Elena Simperl
  • [pdf] Limits of Zero-shot Probing on Object Prediction. Shrestha Ghosh
  • [pdf] Knowledge-centric Prompt Composition for Knowledge Base Construction from Pre-trained Language Models. Xue Li, Anthony James Hughes, Majlinda Llugiqi, Fina Polat, Paul Groth, Fajar J. Ekaputra
  • [pdf] Enhancing Knowledge Base Construction from Pre-trained Language Models using Prompt Ensembles. Fabian Biester, Daniel Del Gaudio, Mohamed Abdelaal
  • [pdf] Broadening BERT vocabulary for Knowledge Graph Construction using Wikipedia2Vec. Debanjali Biswas, Stephan Linzbach, Dimitar Dimitrov, Hajira Jabeen, Stefan Dietze
  • [pdf] LLM2KB: Constructing Knowledge Bases using instruction tuned context aware Large Language Models. Anmol Nayak, Hariprasad Timmapathini

* Challenge subtask winner, will also each give a 10-minute presentation

Program Committee

  • Hang Dong, University of Oxford
  • Russa Biswas, FIZ Karlsruhe
  • Jiaoyan Chen, University of Manchester
  • Gerard de Melo, HPI Potsdam
  • Peter Bloem, Vrije Universiteit Amsterdam
  • Edlira Vakaj, Birmingham City University
  • Stefan Dietze, Heinrich-Heine-Universität Düsseldorf
  • Paul Groth, University of Amsterdam
  • Lucie-Aimée Kaffee, HPI Potsdam
  • Hiba Arnaout, MPI for Informatics
  • Shrestha Ghosh, MPI for Informatics
  • Frank van Harmelen, Vrije Universiteit Amsterdam
  • Heiko Paulheim, Mannheim University
  • Janna Omeliyanenko, University of Würzburg
  • Vanessa López, IBM Research
  • Martin Nečaský, Charles University Prague


Simon Razniewski
Bosch Center for AI
Sneha Singhania
MPI Informatics
Jeff Z. Pan
University of Edinburgh
Huawei Technology R&D UK