Katja Filippova

48 papers A* 10A 2B 3Journal 19Unranked 13

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Language Models Struggle to Use Representations Learned In-Context. CoRR Michael A. Lepori, Tal Linzen, Ann Yuan, Katja Filippova
2026	J	`jnl`	Think Before You Lie: How Reasoning Leads to Honesty. CoRR Ann Yuan, Asma Ghandeharioun, Carter Blum, Alicia Machado, Jessica Hoffmann, Daphne Ippolito, Martin Wattenberg, Lucas Dixon, Katja Filippova
2025	J	`jnl`	Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics. CoRR Carter Blum, Katja Filippova, Ann Yuan, Asma Ghandeharioun, Julian Zimmert, Fred Zhang, Jessica Hoffmann, Tal Linzen, Martin Wattenberg, Lucas Dixon, Mor Geva
2024	J	`jnl`	Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice. CoRR A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski, Katja Filippova, Ken Ziyu Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Niloofar Mireshghallah, Ilia Shumailov, Eleni Triantafillou, Peter Kairouz, Nicole Mitchell, Percy Liang, Daniel E. Ho, Yejin Choi, Sanmi Koyejo, Fernando A. Delgado, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Solon Barocas, Amy Cyphert, Mark A. Lemley, danah boyd, Jennifer Wortman Vaughan, Miles Brundage, David Bau, Seth Neel, Abigail Z. Jacobs, Andreas Terzis, Hanna M. Wallach, Nicolas Papernot, Katherine Lee
2023	—	`conf`	Diagnosing AI Explanation Methods with Folk Concepts of Behavior. FAccT Alon Jacovi, Jasmijn Bastings, Sebastian Gehrmann, Yoav Goldberg, Katja Filippova
2023	J	`jnl`	Diagnosing AI Explanation Methods with Folk Concepts of Behavior. J. Artif. Intell. Res. Alon Jacovi, Jasmijn Bastings, Sebastian Gehrmann, Yoav Goldberg, Katja Filippova
2023	A*	`conf`	Dissecting Recall of Factual Associations in Auto-Regressive Language Models. EMNLP Mor Geva, Jasmijn Bastings, Katja Filippova, Amir Globerson
2023	J	`jnl`	Dissecting Recall of Factual Associations in Auto-Regressive Language Models. CoRR Mor Geva, Jasmijn Bastings, Katja Filippova, Amir Globerson
2023	J	`jnl`	Make Every Example Count: On Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets. CoRR Irina Bejan, Artem Sokolov, Katja Filippova
2023	A*	`conf`	Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets. EMNLP Irina Bejan, Artem Sokolov, Katja Filippova
2023	A*	`conf`	Theoretical and Practical Perspectives on what Influence Functions Do. NeurIPS Andrea Schioppa, Katja Filippova, Ivan Titov, Polina Zablotskaia
2023	J	`jnl`	Theoretical and Practical Perspectives on what Influence Functions Do. CoRR Andrea Schioppa, Katja Filippova, Ivan Titov, Polina Zablotskaia
2022	A*	`conf`	"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification. EMNLP Jasmijn Bastings, Sebastian Ebert, Polina Zablotskaia, Anders Sandholm, Katja Filippova
2022	J	`jnl`	Diagnosing AI Explanation Methods with Folk Concepts of Behavior. CoRR Alon Jacovi, Jasmijn Bastings, Sebastian Gehrmann, Yoav Goldberg, Katja Filippova
2022	J	`jnl`	Understanding Text Classification Data and Models Using Aggregated Input Salience. CoRR Sebastian Ebert, Alice Shoshana Jakobovits, Katja Filippova
2021	J	`jnl`	"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification. CoRR Jasmijn Bastings, Sebastian Ebert, Polina Zablotskaia, Anders Sandholm, Katja Filippova
2021	—	`conf`	Controlling Machine Translation for Multiple Attributes with Additive Interventions. EMNLP (1) Andrea Schioppa, David Vilar, Artem Sokolov, Katja Filippova
2021	A	`conf`	We Need To Talk About Random Splits. EACL Anders Søgaard, Sebastian Ebert, Jasmijn Bastings, Katja Filippova
2020	—	`conf`	Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data. EMNLP (Findings) Katja Filippova
2020	J	`jnl`	Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data. CoRR Katja Filippova
2020	—	`conf`	The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? BlackboxNLP@EMNLP Jasmijn Bastings, Katja Filippova
2020	J	`jnl`	The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? CoRR Jasmijn Bastings, Katja Filippova
2020	J	`jnl`	We Need to Talk About Random Splits. CoRR Anders Søgaard, Sebastian Ebert, Jasmijn Bastings, Katja Filippova
2018	J	`jnl`	Eval all, trust a few, do wrong to none: Comparing sentence generation models. CoRR Ondrej Cífka, Aliaksei Severyn, Enrique Alfonseca, Katja Filippova
2018	B	`conf`	Sentence-Level Fluency Evaluation: References Help, But Can Be Spared! CoNLL Katharina Kann, Sascha Rothe, Katja Filippova
2018	J	`jnl`	Sentence-Level Fluency Evaluation: References Help, But Can Be Spared! CoRR Katharina Kann, Sascha Rothe, Katja Filippova
2016	J	`jnl`	Multi-lingual opinion mining on YouTube. Inf. Process. Manag. Aliaksei Severyn, Alessandro Moschitti, Olga Uryupina, Barbara Plank, Katja Filippova
2015	J	`jnl`	Fast k-best Sentence Compression. CoRR Katja Filippova, Enrique Alfonseca
2015	—	`conf`	Idest: Learning a Distributed Representation for Event Patterns. HLT-NAACL Sebastian Krause, Enrique Alfonseca, Katja Filippova, Daniele Pighin
2015	A*	`conf`	Sentence Compression by Deletion with LSTMs. EMNLP Katja Filippova, Enrique Alfonseca, Carlos A. Colmenares, Lukasz Kaiser, Oriol Vinyals
2014	—	`conf`	Modelling Events through Memory-based, Open-IE Patterns for Abstractive Summarization. ACL (1) Daniele Pighin, Marco Cornolti, Enrique Alfonseca, Katja Filippova
2014	—	`conf`	Opinion Mining on YouTube. ACL (1) Aliaksei Severyn, Alessandro Moschitti, Olga Uryupina, Barbara Plank, Katja Filippova
2013	A*	`conf`	Overcoming the Lack of Parallel Data in Sentence Compression. EMNLP Katja Filippova, Yasemin Altun
2012	—	`conf`	Pattern Learning for Relation Extraction with a Hierarchical Topic Model. ACL (2) Enrique Alfonseca, Katja Filippova, Jean-Yves Delort, Guillermo Garrido
2012	—	`conf`	User Demographics and Language in an Implicit Social Network. EMNLP-CoNLL Katja Filippova
2011	A*	`conf`	Improved video categorization from text metadata and user comments. SIGIR Katja Filippova, Keith B. Hall
2011	—	`ed.`	Proceedings of the Workshop on Monolingual Text-To-Text Generation@ACL, Portland, Oregon, USA, June 24, 2011 Monolingual@ACL Katja Filippova, Stephen Wan
2010	B	`conf`	Multi-Sentence Compression: Finding Shortest Paths in Word Graphs. COLING Katja Filippova
2009	A	`conf`	Company-Oriented Extractive Summarization of Financial News. EACL Katja Filippova, Mihai Surdeanu, Massimiliano Ciaramita, Hugo Zaragoza
2009	—	`conf`	Summarizing with Encyclopedic Knowledge. TAC Vivi Nastase, Katja Filippova, David N. Milne
2009	—	`conf`	Tree Linearization in English: Improving Language Model Based Approaches. HLT-NAACL (Short Papers) Katja Filippova, Michael Strube
2008	B	`conf`	Dependency Tree Based Sentence Compression. INLG Katja Filippova, Michael Strube
2008	—	`conf`	Generating Update Summaries with Spreading Activation. TAC Vivi Nastase, Katja Filippova, Simone Paolo Ponzetto
2008	A*	`conf`	Sentence Fusion via Dependency Graph Compression. EMNLP Katja Filippova, Michael Strube
2007	—	`conf`	Extending the Entity-grid Coherence Model to Semantically Related Entities. ENLG Katja Filippova, Michael Strube
2007	A*	`conf`	Generating Constituent Order in German Clauses. ACL Katja Filippova, Michael Strube
2007	J	`jnl`	The German Vorfeld and Local Coherence. J. Log. Lang. Inf. Katja Filippova, Michael Strube
2006	A*	`conf`	Using linguistically motivated features for paragraph boundary identification. EMNLP Katja Filippova, Michael Strube