Martin Tutek
17 papers · 2016–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
๐ Academic Marathon (9) ๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ Conference Polyglot (6) ๐ Cross-Pollinator (6)
๐
Conference Polyglot
(6)
๐
Academic Marathon
(9)
๐
Renaissance Researcher
(7)
๐ฅ
Mega-Team
(23)
๐ฅ
Unstoppable
(5)
โ
The Questioner
๐
Century Club
(14)
๐๏ธ
Keyword Collector
(72)
โก
Prolific Year
(5)
Conferences
ACL (6)
EMNLP (4)
EACL (2)
SEMEVAL (2)
AAAI (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
machine unlearning
(2)
question answering
(2)
chain of thought
(2)
neural network interpretability
(2)
attention mechanism
(2)
sentiment analysis
(2)
sequence classification
(2)
word embedding
(2)
entity tracking
(2)
language model
(2)
logical reasoning
(1)
chain-of-thought reasoning
(1)
information retrieval
(1)
multimodal learning
(1)
model calibration
(1)
social media analysis
(1)
model editing
(1)
in-context learning
(1)
text classification
(1)
feature attribution
(1)
Papers
CRISP: Persistent Concept Unlearning via Sparse Autoencoders
ACL 2026
PRAGWORLD: A Benchmark Evaluating LLMsโ Local World Model Under Minimal Linguistic Alterations and Conversational Dynamics
AAAI 2026
Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models
EACL 2026
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
EMNLP 2025
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
ACL 2025
Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
ACL 2025
Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
EMNLP 2025
MIB: A Mechanistic Interpretability Benchmark
ICML 2025
CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration
EACL 2024
Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
ICLR 2024
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
EMNLP 2024
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods
ACL 2023
NLPOP: a Dataset for Popularity Prediction of Promoted NLP Research on Twitter
ACL 2022
Staying True to Your Word: (How) Can Attention Become Explanation?
ACL 2020
Iterative Recursive Attention Model for Interpretable Sequence Classification
EMNLP 2018
TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news
SEMEVAL 2017
TakeLab at SemEval-2016 Task 6: Stance Classification in Tweets Using a Genetic Algorithm Based Ensemble
SEMEVAL 2016