Martin Tutek

According to our database, Martin Tutek authored at least 21 papers between 2016 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs.

Adi Simhi, Jonathan Herzig, Martin Tutek, Itay Itzhak, Idan Szpektor, Yonatan Belinkov

CoRR, October, 2025

Context Parametrization with Compositional Adapters.

Josip Jukic, Martin Tutek, Jan Snajder

CoRR, September, 2025

CRISP: Persistent Concept Unlearning via Sparse Autoencoders.

Tomer Ashuach, Dana Arad, Aaron Mueller, Martin Tutek, Yonatan Belinkov

CoRR, August, 2025

Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings.

David Dukic, Ana Baric, Marko Culjak, Josip Jukic, Martin Tutek

CoRR, June, 2025

Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps.

Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, Yonatan Belinkov

CoRR, February, 2025

MIB: A Mechanistic Interpretability Benchmark.

Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fried Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov

Proceedings of the Forty-second International Conference on Machine Learning, 2025

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space.

Tomer Ashuach, Martin Tutek, Yonatan Belinkov

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness.

Fran Jelenic, Josip Jukic, Martin Tutek, Mate Puljiz, Jan Snajder

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs.

Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration.

Rachneet Sachdeva, Martin Tutek, Iryna Gurevych

Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024

2023

Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods.

Josip Jukic, Martin Tutek, Jan Snajder

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

Extending the recurrent neural network model for improved compositional modelling of text sequences ; Proširenje modela povratnih neuronskih mreža za poboljšano kompozicijsko modeliranje tekstnih sljedova.

Martin Tutek

PhD thesis, 2022

Toward Practical Usage of the Attention Mechanism as a Tool for Interpretability.

Martin Tutek, Jan Snajder

IEEE Access, 2022

NLPOP: a Dataset for Popularity Prediction of Promoted NLP Research on Twitter.

Leo Obadic, Martin Tutek, Jan Snajder

Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, 2022

2020

Staying True to Your Word: (How) Can Attention Become Explanation?

Martin Tutek, Jan Snajder

Proceedings of the 5th Workshop on Representation Learning for NLP, 2020

2018

Iterative Recursive Attention Model for Interpretable Sequence Classification.

Martin Tutek, Jan Snajder

Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, 2018

2017

TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news.

Leon Rotim, Martin Tutek, Jan Snajder

Proceedings of the 11th International Workshop on Semantic Evaluation, 2017

Predicting News Values from Headline Text and Emotions.

Maria Pia di Buono, Jan Snajder, Bojana Dalbelo Basic, Goran Glavas, Martin Tutek, Natasa Milic-Frayling

Proceedings of the 2017 Workshop: Natural Language Processing meets Journalism, 2017

Two Layers of Annotation for Representing Event Mentions in News Stories.

Maria Pia di Buono, Martin Tutek, Jan Snajder, Goran Glavas, Bojana Dalbelo Basic, Natasa Milic-Frayling

Proceedings of the 11th Linguistic Annotation Workshop, 2017

2016

TakeLab at SemEval-2016 Task 6: Stance Classification in Tweets Using a Genetic Algorithm Based Ensemble.

Martin Tutek, Ivan Sekulic, Paula Gombar, Ivan Paljak, Filip Culinovic, Filip Boltuzic, Mladen Karan, Domagoj Alagic, Jan Snajder

Proceedings of the 10th International Workshop on Semantic Evaluation, 2016

Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base.

Martin Tutek, Goran Glavas, Jan Snajder, Natasa Milic-Frayling, Bojana Dalbelo Basic

Proceedings of the 25th ACM International Conference on Information and Knowledge Management, 2016