Martin Tutek - RankMe

36 papers A* 5A 1Journal 18Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Old Habits Die Hard: How Conversational History Geometrically Traps LLMs. CoRR Adi Simhi, Fazl Barez, Martin Tutek, Yonatan Belinkov, Shay B. Cohen
2026	A*	`conf`	PRAGWORLD: A Benchmark Evaluating LLMs' Local World Model Under Minimal Linguistic Alterations and Conversational Dynamics. AAAI Sachin Vashistha, Aryan Bibhuti, Atharva Naik, Martin Tutek, Somak Aditya
2026	—	`conf`	Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models. EACL (Findings) Matija Luka Kukic, Marko Culjak, David Dukic, Martin Tutek, Jan Snajder
2026	J	`jnl`	Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models. CoRR Matija Luka Kukic, Marko Culjak, David Dukic, Martin Tutek, Jan Snajder
2025	J	`jnl`	CRISP: Persistent Concept Unlearning via Sparse Autoencoders. CoRR Tomer Ashuach, Dana Arad, Aaron Mueller, Martin Tutek, Yonatan Belinkov
2025	J	`jnl`	Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings. CoRR David Dukic, Ana Baric, Marko Culjak, Josip Jukic, Martin Tutek
2025	J	`jnl`	Context Parametrization with Compositional Adapters. CoRR Josip Jukic, Martin Tutek, Jan Snajder
2025	J	`jnl`	Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models. CoRR Dana Arad, Yonatan Belinkov, Hanjie Chen, Najoung Kim, Hosein Mohebbi, Aaron Mueller, Gabriele Sarti, Martin Tutek
2025	A*	`conf`	MIB: A Mechanistic Interpretability Benchmark. ICML 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
2025	J	`jnl`	MIB: A Mechanistic Interpretability Benchmark. CoRR Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden 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
2025	J	`jnl`	ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs. CoRR Adi Simhi, Jonathan Herzig, Martin Tutek, Itay Itzhak, Idan Szpektor, Yonatan Belinkov
2025	A*	`conf`	Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps. EMNLP Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, Yonatan Belinkov
2025	J	`jnl`	Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps. CoRR Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, Yonatan Belinkov
2025	J	`jnl`	PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics. CoRR Sachin Vashistha, Aryan Bibhuti, Atharva Naik, Martin Tutek, Somak Aditya
2025	—	`conf`	REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space. ACL (Findings) Tomer Ashuach, Martin Tutek, Yonatan Belinkov
2024	—	`conf`	CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration. EACL (1) Rachneet Sachdeva, Martin Tutek, Iryna Gurevych
2024	A*	`conf`	Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. EMNLP Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych
2024	J	`jnl`	Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. CoRR Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych
2024	A*	`conf`	Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness. ICLR Fran Jelenic, Josip Jukic, Martin Tutek, Mate Puljiz, Jan Snajder
2024	J	`jnl`	REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space. CoRR Tomer Ashuach, Martin Tutek, Yonatan Belinkov
2023	J	`jnl`	CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration. CoRR Rachneet Sachdeva, Martin Tutek, Iryna Gurevych
2023	—	`conf`	Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods. ACL (Findings) Josip Jukic, Martin Tutek, Jan Snajder
2023	J	`jnl`	Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness. CoRR Fran Jelenic, Josip Jukic, Martin Tutek, Mate Puljiz, Jan Snajder
2022	J	`jnl`	Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods. CoRR Josip Jukic, Martin Tutek, Jan Snajder
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
2022	—	`conf`	NLPOP: a Dataset for Popularity Prediction of Promoted NLP Research on Twitter. WASSA@ACL Leo Obadic, Martin Tutek, Jan Snajder
2022	J	`jnl`	Toward Practical Usage of the Attention Mechanism as a Tool for Interpretability. IEEE Access Martin Tutek, Jan Snajder
2020	—	`conf`	Staying True to Your Word: (How) Can Attention Become Explanation? RepL4NLP@ACL Martin Tutek, Jan Snajder
2020	J	`jnl`	Staying True to Your Word: (How) Can Attention Become Explanation? CoRR Martin Tutek, Jan Snajder
2018	—	`conf`	Iterative Recursive Attention Model for Interpretable Sequence Classification. BlackboxNLP@EMNLP Martin Tutek, Jan Snajder
2018	J	`jnl`	Iterative Recursive Attention Model for Interpretable Sequence Classification. CoRR Martin Tutek, Jan Snajder
2017	—	`conf`	Predicting News Values from Headline Text and Emotions. NLPmJ@EMNLP Maria Pia di Buono, Jan Snajder, Bojana Dalbelo Basic, Goran Glavas, Martin Tutek, Natasa Milic-Frayling
2017	—	`conf`	TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news. SemEval@ACL Leon Rotim, Martin Tutek, Jan Snajder
2017	—	`conf`	Two Layers of Annotation for Representing Event Mentions in News Stories. LAW@ACL Maria Pia di Buono, Martin Tutek, Jan Snajder, Goran Glavas, Bojana Dalbelo Basic, Natasa Milic-Frayling
2016	A	`conf`	Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base. CIKM Martin Tutek, Goran Glavas, Jan Snajder, Natasa Milic-Frayling, Bojana Dalbelo Basic
2016	—	`conf`	TakeLab at SemEval-2016 Task 6: Stance Classification in Tweets Using a Genetic Algorithm Based Ensemble. SemEval@NAACL-HLT Martin Tutek, Ivan Sekulic, Paula Gombar, Ivan Paljak, Filip Culinovic, Filip Boltuzic, Mladen Karan, Domagoj Alagic, Jan Snajder