Education Research Current About VU Amsterdam NL
Bachelor's programmes Master's programmes VU for Professionals
Exchange programme VU Amsterdam Summer School Honours Programme Dutch language courses (NT2) Semester in Amsterdam
PhD at VU Amsterdam Featured research Prizes and distinctions
Interdisciplinary research institutes Scientists of VU Amsterdam Research Impact Support Portal Create impact with your research
News Events calendar Moving towards a healthier future
VU UPDATE: Situation in Israel and the Palestinian regions Culture at VU Amsterdam
Practical matters Mission, core values and vision Entrepreneurship on VU Campus
Governance of VU Amsterdam Valorisation and impact Partnering with VU Amsterdam VU Alumni Community Take a look at our vacancies!
Sorry! De informatie die je zoekt, is enkel beschikbaar in het Engels.
This programme is saved in My Study Choice.
Something went wrong with processing the request.
Something went wrong with processing the request.

PhD defence J.B. Kamp

Share

Interpreting the Methods that Interpret Language Models

The Same AI, Four Different Explanations: Research Reveals Hidden Patterns Behind AI Explanations

AI is increasingly capable of making important decisions, but explaining why an AI model arrives at a particular decision proves to be less straightforward. Research by computational linguist Jonathan Kamp shows that different explanatory methods can provide different explanations for exactly the same AI decision. Moreover, these differences are not random: they often follow fixed patterns.

Artificial intelligence (AI) is increasingly being deployed for important applications, such as text evaluation, medical support, and detecting harmful online content. Therefore, methods have been developed to attempt to explain the 'reasoning' of an AI.

Kamp shows that this explanation is not always reliable. The differences between explanatory methods depend on the chosen method, the type of AI model, and the task the model performs. Furthermore, AI models can sometimes reach the correct outcome based on incorrect clues in a text.

Do Not Trust Blindly

By mapping the systematic patterns and biases in AI explanations, it becomes clearer when an explanation is reliable or, conversely, less reliable. The main conclusion is therefore that we should not simply trust AI explanations, but evaluate them critically.

The results are important for developers, companies, and users of AI systems who want to make reliable decisions. AI models must not only perform well but also be able to reliably explain why they make certain choices.

This is becoming increasingly relevant now that large language models such as chatbots are being used more frequently in education, healthcare, and information provision. For example, with an AI assistant providing medical information, it is possible to check which sources and text fragments influence the decision. This allows users to better assess whether the information is reliable.

More information on the thesis

Programme

PhD defence by J.B. Kamp

PhD Faculty of Social Sciences and Humanities

Supervisors:

  • prof.dr. A.S. Fokkens
  • prof.dr. L.M. Beinborn

The PhD defence can be followed online as well

About PhD defence J.B. Kamp

Starting date

  • 18 September 2026

Time

  • 09:45 - 11:15

Location

  • Main building VU, Aula

Address

  • De Boelelaan 1105, 1081 HV Amsterdam

Follow the ceremony online

Go to livestream

Quick links

Homepage VU Amsterdam Culture at VU Amsterdam University Library Dashboard

Study

Academic calendar Study Guide Timetable Canvas

Featured

Donate to the VU Fund VU Magazine Ad Valvas Digital accessibility

About VU Amsterdam

Contact with VU Amsterdam Take a look at our vacancies! Faculties VU Amsterdam Divisions VU Amsterdam
Privacy Disclaimer Safety Web Colophon Cookie settings Web Archive

Copyright © VU