Martin Tutek
@mtutek.bsky.social
Postdoc @ TakeLab, UniZG | previously: Technion; TU Darmstadt | PhD @ TakeLab, UniZG
Faithful explainability, controllability & safety of LLMs.
🔎 On the academic job market 🔎
https://mttk.github.io/
Faithful explainability, controllability & safety of LLMs.
🔎 On the academic job market 🔎
https://mttk.github.io/
I'd like a link as well!
January 15, 2026 at 9:20 AM
I'd like a link as well!
wait this is not the routine?
November 27, 2025 at 5:42 PM
wait this is not the routine?
within the next 3-4 days, so sadly that doesn't work
November 11, 2025 at 11:03 AM
within the next 3-4 days, so sadly that doesn't work
Reposted by Martin Tutek
Outstanding paper (5/7):
"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps"
by Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, and Yonatan Belinkov
aclanthology.org/2025.emnlp-m...
6/n
"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps"
by Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, and Yonatan Belinkov
aclanthology.org/2025.emnlp-m...
6/n
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, Yonatan Belinkov. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
aclanthology.org
November 7, 2025 at 10:32 PM
Outstanding paper (5/7):
"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps"
by Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, and Yonatan Belinkov
aclanthology.org/2025.emnlp-m...
6/n
"Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps"
by Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, and Yonatan Belinkov
aclanthology.org/2025.emnlp-m...
6/n
Thank you Gabriele :)
November 7, 2025 at 10:52 AM
Thank you Gabriele :)