Katerina Margatina

27 papers A* 2A 2Journal 14Unranked 9

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	A Study on Leveraging Search and Self-Feedback for Agent Reasoning. CoRR Karthikeyan K, Michelle Yuan, Elman Mansimov, Katerina Margatina, Anurag Pratik, Daniele Bonadiman, Monica Sunkara, Yi Zhang, Yassine Benajiba
2025	—	`conf`	CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions. ACL (1) Tamer Alkhouli, Katerina Margatina, James Gung, Raphael Shu, Claudia Zaghi, Monica Sunkara, Yi Zhang
2025	J	`jnl`	CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions. CoRR Tamer Alkhouli, Katerina Margatina, James Gung, Raphael Shu, Claudia Zaghi, Monica Sunkara, Yi Zhang
2024	A*	`conf`	The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models. NeurIPS Hannah Rose Kirk, Alexander Whitefield, Paul Röttger, Andrew M. Bean, Katerina Margatina, Rafael Mosquera Gómez, Juan Ciro, Max Bartolo, Adina Williams, He He, Bertie Vidgen, Scott Hale
2024	J	`jnl`	The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models. CoRR Hannah Rose Kirk, Alexander Whitefield, Paul Röttger, Andrew M. Bean, Katerina Margatina, Juan Ciro, Rafael Mosquera, Max Bartolo, Adina Williams, He He, Bertie Vidgen, Scott A. Hale
2023	—	`conf`	Active Learning Principles for In-Context Learning with Large Language Models. EMNLP (Findings) Katerina Margatina, Timo Schick, Nikolaos Aletras, Jane Dwivedi-Yu
2023	J	`jnl`	Active Learning Principles for In-Context Learning with Large Language Models. CoRR Katerina Margatina, Timo Schick, Nikolaos Aletras, Jane Dwivedi-Yu
2023	A	`conf`	Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views. EACL Katerina Margatina, Shuai Wang, Yogarshi Vyas, Neha Anna John, Yassine Benajiba, Miguel Ballesteros
2023	J	`jnl`	Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views. CoRR Katerina Margatina, Shuai Wang, Yogarshi Vyas, Neha Anna John, Yassine Benajiba, Miguel Ballesteros
2023	A	`conf`	Investigating Multi-source Active Learning for Natural Language Inference. EACL Ard Snijders, Douwe Kiela, Katerina Margatina
2023	J	`jnl`	Investigating Multi-source Active Learning for Natural Language Inference. CoRR Ard Snijders, Douwe Kiela, Katerina Margatina
2023	—	`conf`	On the Limitations of Simulating Active Learning. ACL (Findings) Katerina Margatina, Nikolaos Aletras
2023	J	`jnl`	On the Limitations of Simulating Active Learning. CoRR Katerina Margatina, Nikolaos Aletras
2023	A*	`conf`	Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance? EMNLP Ahmed Alajrami, Katerina Margatina, Nikolaos Aletras
2023	J	`jnl`	Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance? CoRR Ahmed Alajrami, Katerina Margatina, Nikolaos Aletras
2022	—	`conf`	Challenges and Strategies in Cross-Cultural NLP. ACL (1) Daniel Hershcovich, Stella Frank, Heather C. Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, Anders Søgaard
2022	J	`jnl`	Challenges and Strategies in Cross-Cultural NLP. CoRR Daniel Hershcovich, Stella Frank, Heather C. Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, Anders Søgaard
2022	—	`conf`	On the Importance of Effectively Adapting Pretrained Language Models for Active Learning. ACL (2) Katerina Margatina, Loïc Barrault, Nikolaos Aletras
2021	—	`conf`	Active Learning by Acquiring Contrastive Examples. EMNLP (1) Katerina Margatina, Giorgos Vernikos, Loïc Barrault, Nikolaos Aletras
2021	J	`jnl`	Active Learning by Acquiring Contrastive Examples. CoRR Katerina Margatina, Giorgos Vernikos, Loïc Barrault, Nikolaos Aletras
2021	J	`jnl`	Bayesian Active Learning with Pretrained Language Models. CoRR Katerina Margatina, Loïc Barrault, Nikolaos Aletras
2021	—	`conf`	Frustratingly Simple Pretraining Alternatives to Masked Language Modeling. EMNLP (1) Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras
2021	J	`jnl`	Frustratingly Simple Pretraining Alternatives to Masked Language Modeling. CoRR Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras
2020	—	`conf`	Domain Adversarial Fine-Tuning as an Effective Regularizer. EMNLP (Findings) Giorgos Vernikos, Katerina Margatina, Alexandra Chronopoulou, Ion Androutsopoulos
2020	J	`jnl`	Domain Adversarial Fine-Tuning as an Effective Regularizer. CoRR Giorgos Vernikos, Katerina Margatina, Alexandra Chronopoulou, Ion Androutsopoulos
2019	—	`conf`	Attention-based Conditioning Methods for External Knowledge Integration. ACL (1) Katerina Margatina, Christos Baziotis, Alexandros Potamianos
2019	J	`jnl`	Attention-based Conditioning Methods for External Knowledge Integration. CoRR Katerina Margatina, Christos Baziotis, Alexandros Potamianos