Publications // Marzena Karpinska

Preprint

1. "One ruler to measure them all: Benchmarking multilingual long-context language models"
Yekyung Kim, Jenna Russell, Marzena Karpinska, Mohit Iyyer (2025).

Preprint

2. "People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text"
Jenna Russell, Marzena Karpinska, Mohit Iyyer (2025).

Preprint

3. "OverThink: Slowdown Attacks on Reasoning LLMs"
Abhinav Kumar, Jaechul Roh, Ali Naseh, Marzena Karpinska, Mohit Iyyer, Amir Houmansadr, Eugene Bagdasarian (2025).

EMNLP

4. "One Thousand and One Pairs: A "novel" challenge for long-context language models"
Marzena Karpinska, Katherine Thai, Kyle Lo, Tanya Goyal, Mohit Iyyer (2024).

Preprint

5. "CaLMQA: Exploring culturally specific long-form question answering across 23 languages"
Shane Arora*, Marzena Karpinska*, Hung-Ting Chen, Ipsita Bhattacharjee, Mohit Iyyer, Eunsol Choi (2024). *equal contributions

WMT

6. "Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation"
Tom Kocmi, Vilém Zouhar, Eleftherios Avramidis, Roman Grundkiewicz, Marzena Karpinska, Maja Popović, Mrinmaya Sachan, Mariya Shmatova (2024).

COLM

7. "FABLES: Evaluating faithfulness and content selection in book-length summarization"
Yekyung Kim, Yapei Chang, Marzena Karpinska, Aparna Garimella, Varun Manjunatha, Kyle Lo, Tanya Goyal, Mohit Iyyer (2024). (accepted to COLM 2024)

Preprint

8. "Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order"
Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T Stillerman, ..., Sampo Pyysalo (2024).

LREC-COLING

9. "NarrativeTime: Dense Temporal Annotation on a Timeline"
Anna Rogers, Marzena Karpinska, Ankita Gupta, Vladislav Lialin, Gregory Smelkov, Anna Rumshisky (2024). The 2024 Joint International Conference on Computiational Linguistics, Language, Resources and Evaluation.

WMT

10. "Large language models effectively leverage document-level context for literary translation, but critical errors persist"
Marzena Karpinska and Mohit Iyyer (2023). Proceedings of the Eighth Conference on Machine Translation.

NeurIPS

11. "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense"
Kalpesh Krishna, Yixiao Song, Marzena Karpinska, John Wieting, Mohit Iyyer (2023). Thirty-seventh Annual Conference on Neural Information Processing Systems.

ACL: Report

12. "Program Chairs’ Report on Peer Review at ACL 2023" [responsible for data analysis]
Anna Rogers, Marzena Karpinska, Jordan Boyd-Graber, Naoaki Okazaki (2023). Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), xl–lxxv.

EMNLP

13. "DEMETR: Diagnosing Evaluation Metrics for Translation"
Marzena Karpinska, Nishant Raj, Katherine Thai, Yixiao Song, Ankita Gupta, and Mohit Iyyer (2022). Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.

EMNLP

14. "Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature"
Katherine Thai*, Marzena Karpinska*, Kalpesh Krishna, William Ray, Moira Inghilleri, John Wieting, and Mohit Iyyer (2022). Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. *equal contributions

EMNLP

15. "ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution"
Ankita Gupta, Marzena Karpinska, Wenlong Zhao, Kalpesh Krishna, Jack Merullo, Luke Yeh, Mohit Iyyer, and Brendan O'Connor (2022). Findings of the Association for Computational Linguistics: EACL 2023.

COLING

16. "Revisiting Statistical Laws of Semantic Shift in Romance Cognates"
Yoshifumi Kawasaki, Maëlys Salingre, Marzena Karpinska, Hiroya Takamura, and Ryo Nagata (2022). The 29th International Conference on Computational Linguistics.

EMNLP

17. "The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation"
Marzena Karpinska, Nader Akoury, and Mohit Iyyer (2021). Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.

ICPhS

18. “How accented do Caucasian-looking vs. Asian-looking native speakers sound to a Japanese listener?”
Marzena Karpinska (2019). Proceedings of the The International Congress of Phonetic Sciences. Melbourne, Australia: ICPhS.

Routledge

19. “Emoticons: Digital Lingua Franca or a Culture-Specific Product Leading to Misunderstandings?”
Marzena Karpinska, Paula Kurzawska, and Katarzyna Rozanska (2019). Emoticons, Kaomoji, and Emoji: The Transformation of Communication in the Digital Age (Routledge Research in Language and Communication). Ed. by E. Giannoulis and Lukas R.A. Wilde.

KJEE

20. "The Discourse of Kyōyō and English Education in Japan"
Kimie Yamamura, Ryo Gakutani, Marzena Karpinska, Tetsuro Tanojiri, and Tom Gally (2019). Komaba Journal of English Education. Department of English Language, The University of Tokyo, Komaba.

RelNLP

21. “Subcharacter Information in Japanese Embeddings: When Is It Worth It?”
Marzena Karpinska, Bofang Li, Anna Rogers, and Aleksandr Drozd (2018). Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP. Melbourne, Australia: ACL, pp. 28–37.

ICPhS

22. “Vowel perception by listeners from different English dialects”
Marzena Karpinska, Shodai Uchida, and Izabelle Grenon (2015). Proceedings of the The International Congress of Phonetic Sciences. Glasgow, Scotland: ICPhS.

ANLP

23. 分散表現を用いたロマンス語同源語動詞の意味変化の分析 (Analysis of Semantic Shift in Romance Cognate Verbs Using Word Embeddings)
Kawasaki Yoshifumi, Maëlys Salingre, Marzena Karpinska, Takamura Hiroya, Nagata Ryo (2022). Proceedings of the 28th Annual Conference of the Association for Natural Language Processing. Hamamatsu, Japan. (committee award for novelty)