What if AI agents aren't here to replace us, but to facilitate our decisions? In a study with 1600 participants, we show that a human with action choices narrowed by an AI makes better sequential decisions than an AI or a human alone.
📜 arxiv.org/abs/2510.16097

todo:
* thesis defense ✅

Grateful to the committee and reviewers Marius Kloft, @arkrause.bsky.social, @rupakmajumdar.bsky.social, and @tobigerstenberg.bsky.social for their time and support. No words are enough to thank my advisor @autreche.bsky.social for everything I’ve learned from him so far 🙏

Last week I had the pleasure of presenting a 2.5-hour tutorial on "Counterfactuals in Minds and Machines" at UAI 2025 in Rio 🇧🇷, prepared together with @autreche.bsky.social and @tobigerstenberg.bsky.social. We've made all materials and references available here: learning.mpi-sws.org/counterfactu...

In Athens 🇬🇷 for the Greeks in AI symposium. Super excited to present our work on "Counterfactual Token Generation in LLMs" (bit.ly/4nMibs2) and see all the amazing work Greek people all over the world are doing on AI! If you are in Athens, let's meet! Next, heading to👇

The LLM API you use returns (and charges you for) 5 tokens. Did the LLM actually generate 5 tokens? Or is the provider overcharging you? 🤔 In arxiv.org/abs/2505.21627, led by Ander Artola Velasco, we argue (game-theoretically) for a change from pay-per-token to pay-per-character.

In Singapore for #ICLR2025! I'll be presenting our work on a causal methodology for evaluating LLMs (arxiv.org/abs/2502.01754) at the "Building Trust in LLMs" workshop on Monday. If you are working on causality, game theory and/or LLMs, let's grab a ☕️ during the conference!

What would an LLM have said, counterfactually? Here is a short video illustrating our method for counterfactual token generation. We will present this work at the CaLM workshop at #neurips2024. See you in Vancouver!
📜 arxiv.org/abs/2409.17027
💻 made with manim in python

Hey there 🦋
Let's start with an intro. I'm a final-year PhD student at the Max Planck Institute for Software Systems, working on machine learning, decision making and social aspects of AI. Currently on the academic job market, looking for tenure-track positions👇
💻 stsirtsis.github.io