Jan-Christoph Kalo

Hi, I am Jan-Christoph Kalo, Assistant Professor at the University of Amsterdam in the Intelligent Data Engineering Lab (INDElab).

Research · Publications · Google Scholar · Email

My research studies what happens at the boundaries between different representations of knowledge. The same fact can live as a sentence in text, a row in a statistical table, a triple in a knowledge graph, a SQL query, a logical formula, or somewhere in the parameters of a language model — and moving between these forms is often lossy and context-dependent. Whether two representations actually encode the same knowledge depends on what population, time frame, or scope is assumed, and integrating them means making those assumptions explicit: this is what I call knowledge translation.

I work at the intersection of language models, knowledge graphs, and databases, combining semantic web, database, and NLP techniques. Expressing the same knowledge in multiple forms and studying where the versions disagree is a diagnostic — it tells us what each representation captures, what it silently drops, and where context is doing hidden work. The full portfolio of projects is on the Research page.

Beyond research, I teach databases in the Bachelor programme at UvA and supervise MSc and PhD projects. I currently supervise the PhD candidates Fabian Hoppe (deductive reasoning with LLMs; VU Amsterdam, LEMUR doctoral network), Trevor Pearce (knowledge graph construction from conversational data; UvA), and Lucas Lageweg (text-to-SQL over official statistics, with Statistics Netherlands). I have supervised more than 45 BSc and MSc theses, including winners of the ADS Thesis Award (2022) and the best AI bachelor thesis award of Lower Saxony (2019).

I co-organise the Dagstuhl Seminar “Large Language Models Meet Knowledge Graphs” (October 2026), the AKBC workshop, and the LM-KBC challenge on knowledge base construction from language models. I am part of the management team of the COST Action KGELL (CA24121), active in the COST Action GOBLIN (CA23147) on large-scale open multilingual knowledge graphs, and a contributor to the ISWS summer school.

Talks & tutorials

• Hands-on tutorial “LLM4KGC”, SIKS & HI Course on Knowledge Graphs, online, June 2026
• Tutorials at the International Semantic Web Summer School (ISWS), Bertinoro — 2024 and 2025
• Invited talk, GOBLIN COST Action meeting, Prague, February 2025
• Keynote “What do Language Models Know About the World?”, X-TAIL Workshop at EKAW 2024, Amsterdam
• Invited lecture, FoMo Lectures, University of Amsterdam, June 2023

Resources

• LOCuST — a multilingual benchmark for text-to-SQL over official statistics
• LM-KBC challenge datasets — knowledge base construction from language models
• KAMEL — a probing benchmark with multi-token entities
• KnowlyBERT — hybrid query answering over language models and knowledge graphs
• WILA-PopQA — a popularity-matched multilingual factual-recall benchmark

Before Amsterdam, I did my PhD at TU Braunschweig (2021) on representation heterogeneity in knowledge graphs — the same problem I now call knowledge translation — followed by a postdoc in the Knowledge Representation and Reasoning group at VU Amsterdam. A longer bio for talk introductions is here.