CFA: Workshop on Functions and Representations in AI Systems

Call for Abstracts: Workshop on Functions and Representations in AI Systems

16th–17th November 2026
Copenhagen, Denmark (Carlsberg Academy)
CFA Deadline September 21st

We invite abstract submissions for a workshop on Functions and Representations in AI Systems, to be held in Copenhagen, Denmark November 16th–17th.

Abstracts of 300-500 words will be due 21st September.

The concepts of function and representation are widely invoked in the cognitive and life sciences. An influential philosophical tradition, teleosemantics, proposes to ground representation partly in biological functions and ground functions in historical selection processes. While this remains a leading approach, the account has faced challenges, ranging from the notorious "swampman" objection, to more recent disputes about the nature of functional and representational explanation in scientific practice.

Independently, the recent wave of developments in artificial intelligence has sparked questions about the representational capacities of AI models, e.g. what, if anything, can large language models represent? The emerging field of mechanistic interpretability is replete with function- and representation-talk. But is this talk justified? Are AI models subject to selection processes, in the proper sense? And are the concepts of representation and function deployed here the same as those invoked in the life sciences? Are standard philosophical frameworks adequate for the case of AI? Or should we look elsewhere, e.g. to theorising about artefacts? And what role, if any, do human norms and intentionality play in grounding AI functions and content?

A workshop on these issues, co-funded by the Pioneer Center for Artificial Intelligence (https://www.aicentre.dk/p1-programs/functions-and-representations-in-ai-systems) and the Center for Philosophy of Artificial Intelligence (University of Copenhagen) (https://cpai.ku.dk/), will be held in Copenhagen, November 16th–17th, in the beautiful Carlsberg Academy building (https://www.carlsbergfondet.dk/en/about-the-foundation/our-buildings/the-carlsberg-academy/).

Confirmed speakers include

Rosa Cao (Stanford) (https://sites.google.com/site/luosha/home),

Dimitri Coelho Mollo (Umeå) (https://dimitrimollo.academicwebsite.com/)

Jumbly Grindrod (Reading) (https://philpeople.org/profiles/jumbly-grindrod)

We invite abstracts on these issues for presentation at the workshop. Questions for consideration include (but are not limited to):

• What determines whether a component of an AI model is a representation, and what it represents?
• Does treating a model component as a representation entail ascribing a specific function to that component?
• What grounds the functions of components in AI models? The model's training history? The component's causal-explanatory role? The intentions of the model's designers and/or users?
• Do accounts of function and representation from biology readily translate to AI systems? How might the cases differ?
• In what ways are AI models similar to / different from other kinds of function-bearing artefacts?
• Do current practices in mechanistic interpretability reflect our best philosophical theories of representation and function (and vice versa)?
• To what extent are explanations in mechanistic interpretability normative, and what is the source of that normativity? What role do notions like success/failure, function/malfunction, representation/misrepresentation, accuracy/inaccuracy play in explanations of AI models?

Abstracts of 300-500 words should be sent via email to Iwan Williams ([email protected]) no later than Monday 21st September. Please include your name, institutional affiliation and a short bio (max 150 words) in the body of your email. We look forward receiving your submissions.

Please feel free to forward this information to anyone who you think might be interested in presenting a paper or attending the workshop. A further message will be circulated closer to the time with information about registration.