Knowledge Base Construction from Pre-Trained Language Models

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 2^nd 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.

The proceedings are available at CEUR-WS

Important Dates

Papers due:	August 7 August 14, 2024
Notification to authors:	September 11, 2024
Camera-ready deadline:	September 18, 2024
Workshop dates:	November 12, 2024

Topics

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).

Submission site: https://openreview.net/group?id=swsa.semanticweb.org/ISWC/2024/Workshop/KBC-LM.

Keynote Speakers

Schedule

9:30-9:35	Welcome
9:35-10:20	Keynote 1: Immanuel Trummer
10:20-10:40	Best Paper (regular)
10:40-11:00	Coffee break
11:00-12:20	Paper Session 1 (regular)
12:20-14:00	Lunch break
14:00-14:45	Keynote 2: Heiko Paulheim
14:45-14:55	LM-KBC Challenge Introduction
14:45-15:55	Paper Session 2 (challenge)
15:55-16:15	Coffee break
16:15-17:00	Keynote 3: Janna Omeliyanenko
17:00-17:40	Paper Session 3 (regular)

Best Paper

• [pdf] LLM Store: Leveraging Large Language Models as Sources of Wikidata-Structured Knowledge Marcelo Machado, João M. B. Rodrigues, Guilherme Lima, Sandro Rama Fiorini and Viviane T. da Silva

Paper Session 1

• [pdf] Enriching Ontologies with Disjointness Axioms using Large Language Models Elias Crum, Antonio De Santis, Manon Ovide, Jiaxin Pan, Alessia Pisu, Nicolas Lazzari and Sebastian Rudolph
• [pdf] The Effects of Hallucinations in Synthetic Training Data for Relation Extraction Steven Rogulsky, Nicholas Popovic and Michael Färber
• [pdf] Analyzing Llama 3-based Approach for Axiom Translation from Ontologies Xubing Hao, Licong Cui, Cui Tao, Kirk Roberts and Muhammad Amith
• [pdf] Towards Large Language Models Interacting with Knowledge Graphs Via Function Calling Sven Hertling and Harald Sack

Paper Session 2 (challenge)

• [pdf] LLM Store: A KIF Plugin for Wikidata-Based Knowledge Base Completion via LLMs Marcelo Machado, João M. B. Rodrigues, Guilherme Lima and Viviane T. da Silva
• [pdf] Navigating Nulls, Numbers and Numerous Entities: Robust Knowledge Base Construction from Large Language Models Arunav Das, Nadeen Fathallah and Nicole Obretincheva
• [pdf] KGC-RAG: Knowledge Graph Construction from Large Language Model Using Retrieval-Augmented Generation Thin Prabhong, Natthawut Kertkeidkachorn and Areerat Trongratsameethong

Paper Session 3

• [pdf] Automatic knowledge-graph creation from historical documents: The Chilean dictatorship as a case study Camila Díaz, Jocelyn Dunstan, Lorena Etcheverry, Antonia Fonck, Alejandro Grez, Domingo Mery, Juan Reutter and Hugo Rojas
• [pdf] HybridContextQA: A Hybrid Approach for Complex Question Answering using Knowledge Graph Construction and Context Retrieval with LLMs Ghanshyam Verma, Simanta Sarkar, Devishree Pillai, Hotaka Shiokawa, Hamed Shahbazi, Fiona Veazey, Peter Hubbert, Hui Su and Paul Buitelaar
• [pdf] Prompt engineering for tail prediction in domain-specific knowledge graph completion tasks Davide Mario Ricardo Bara
• [pdf] Ontology Learning for ESCO: Leveraging LLMs to Navigate Labor Dynamics Jarno Vrolijk, Victor Poslavsky, Thijmen Bijl, Maksim Popov, Rana Mahdavi, Mohammad Shokri

Program Committee

• Hang Dong, University of Oxford
• Shrestha Ghosh, MPI for Informatics
• Hiba Arnaout, TU Darmstadt
• Matteo Lissandrini, Aalborg University
• Blerta Veseli, MPI-SWS
• Wen Zhang, Zhejiang University
• Mauro Dragoni, University of Trento

Chairs