Zum Navigationspfad Unterseiten von „Veranstaltungsdetail“ Zur Navigation Zum Schnellzugriff Zum Fuß der Seite mit weiteren Services
Zum Inhalt
Fakultät Humanwissenschaften und Theologie
Studierende sitzt am Arbeitsplatz und schaut auf den Laptop. © Aliona Kardash​/​TU Dortmund

Workshop: Philosophical perspectives on artificial reasoning systems

Beginn: Ende: Veranstaltungsort: Emil-Figge-Straße 50, room 0.442, TU Dortmund Campus
The philosophy department of TU Dortmund is organising a one-day workshop exploring the philosophical dimensions of (limitations of) reasoning in large language models.
Auf dem Bild ist eine weißer, weiblicher Roboter, nachdenkend von der Seite zu sehen. © Rebecca Sadowski, mit KI generiert

Early LLMs were notorious for frequently generating outputs that, to users, appeared to contain basic reasoning errors. However, in recent years, researchers and AI developers have invested much effort in improving the common-sense and formal reasoning capacities of transformer-based models through reinforcement learning and similar techniques. This has led to a generation of 'large reasoning models’ that perform well on various benchmarks of reasoning problems.  Still, questions remain about how we should interpret these capacities. 

  • Do large reasoning models really engage in reasoning, or merely in a statistical approximation of reasoning?
  • What accounts of reasoning are available in the philosophical literature, and are these accounts applicable to LLMs?
  • Do LLMs fare differently with respect different kinds of reasoning (e.g. common-sense reasoning, practical reasoning or counterfactual reasoning)?
  • What are the risks of over-attributing reasoning capacities to LLMs? 

This workshop brings together philosophers who work on these and related questions.

 

Attendance is open to anyone interested. We kindly ask attendees to register in advance by sending an email to Rebecca Sadowski (rebecca.sadowski@tu-dortmund.de) by October 23rd, 2026, stating:

  • Your name
  • Your institution / affiliation

 

Preliminary schedule

09:30-10:00 
Opening

10:00-11:00  
Gregor Betz  (Karlsruhe Institute of Technology) and Joris Graff (TU Dortmund)
What Do We Mean When We Ask if LLMs Can Reason?

11:00-11:30 
Break

11:30-12:30 
Jaroslav Malik (University of Hradec Králové)
TBA

12:30-13:30 
Lunch Break

13:30-14:30  
Mirco Sambrotta (Slovak Academy of Sciences)
Can Statistical Predictions Alone Give Rise to Sapience?

14:30-14:45 
Coffee Break

14:45-15:45  
Cordelia Berz (LMU Munich)
Pearl, Not People? Counterfactual Reasoning in LLMs

15:45-16:00 
Coffee Break

16:00-17:00 
Leonard Dung and Thom-Felix Thormann (Ruhr-University Bochum)
Simulation and deceptive reasoning in LLMs

17:00-17:30 
Closing
 

In Kalender übertragen