Publications

Some of these also have posters.

2026
Findings of the WMT26 Multilingual Instruction Shared Task: Small Models Are Not Yet Polyglots
P. Schmidtová, E. Artemova, S. Aycock, N. Bafna, S. Banga, M. Kaur, T. Kocmi, P. Koehn, D. Liu, N. Luu, S. Papi, B. Savoldi, M. Shmatova, H. Sidh, E. Zerminova, V. Zouhar, M. Züfle, P. Chen
Proceedings of WMT26, pp. 1024–1045
CUNI-UFAL at WMT26 Multilingual Instruction Shared Task
A.M. Papáček, P. Schmidtová
Proceedings of WMT26, pp. 1949–1958
Are LLM Judges Language-Neutral? A Cross-Lingual Meta-Evaluation on Multilingual Summarization
M. Koupaei, A. Esmaeili, M. Khanali, F. Mai, P. Schmidtová
INLG 2026, pp. 1022–1040
CAP: Contrastive Activation Patching for Locating, Comparing, and Steering Neurons in Multilingual LLMs
A. Semenikhin, M. Frey, O. Dušek, L. Flek, P. Schmidtová
INLG 2026 (demo), pp. 1–3
Justify Your Prompts!
E. Calò, D.M. Howcroft, L. Leppänen, S. Mahamood, S. Mille, P. Schmidtová, E. van Miltenburg
Computational Linguistics 52(3), pp. 1317–1329
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
S. Papi, J.G. Gilabert, Z. Hopton, V. Zouhar, C. Escolano, G.I. Gállego, J. Iranzo-Sánchez, A. Kim, D. Macháček, P. Schmidtová, M. Züfle
Transactions of the Association for Computational Linguistics (TACL) 14, pp. 1963–1992
Never Truly Out of Fashion: A Retrospective Look at Evaluation in NLG
P. Schmidtová, S. Mahamood, O. Dušek
1st Symposium on Natural Language Generation Evaluations, pp. 63–72
HotelCheckSpan: A Benchmark Dataset for LLM Faithfulness
P. Schmidtová, O. Dušek, S. Mahamood
LREC 2026, pp. 9973–9987
How Important is ‘Perfect’ English for Machine Translation Prompts?
P. Schmidtová, N. Bafna, S. Aycock, G. Vico, W. Kamzela, K. Hämmerl, V. Zouhar
Findings of EACL 2026, pp. 760–777
LLMs as Span Annotators: A Comparative Study of LLMs and Humans
Z. Kasner, V. Zouhar, P. Schmidtová, I. Kartáč, K. Onderková, O. Plátek, D. Gkatzia, S. Mahamood, O. Dušek, S. Balloccu
First Workshop on Multilingual Multicultural Evaluation @ EACL 2026, pp. 1–22
2025
Do My Eyes Deceive Me? A Survey of Human Evaluations of Hallucinations in NLG
P. Schmidtová, E. Calò, S. Balloccu, D. Gkatzia, R. Huidrom, M. Lango, F. Same, V. Zouhar, S. Mahamood, O. Dušek
INLG 2025
Real-World Summarization: When Evaluation Reaches its Limits
P. Schmidtová, O. Dušek, S. Mahamood
Findings of EMNLP 2025
Findings of the WMT25 Multilingual Instruction Shared Task
T. Kocmi, S. Agrawal, E. Artemova, E. Avramidis, E. Briakou, P. Chen, M. Fadaee, M. Freitag, R. Grundkiewicz, Y. Hou, P. Koehn, J. Kreutzer, S. Mansour, S. Perrella, L. Proietti, P. Riley, E. Sánchez, P. Schmidtová, M. Shmatova, V. Zouhar
Proceedings of WMT25, pp. 414–435
ReproHum #0669-08: Reproducing Sentiment Transfer Evaluation
K. Onderková, M. Lango, P. Schmidtová, O. Dušek
4th Workshop on Generation, Evaluation and Metrics (GEM) @ ACL 2025
2024
Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs Best Paper · EACL 2024
S. Balloccu, P. Schmidtová, M. Lango, O. Dušek
EACL 2024
Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices Best Evaluation Paper · INLG 2024
P. Schmidtová, S. Mahamood, S. Balloccu, O. Dušek, A. Gatt, D. Gkatzia, D.M. Howcroft, O. Plátek, A. Sivaprasad
INLG 2024
factgenie: A Framework for Span-Based Evaluation of Generated Texts
Z. Kasner, O. Plátek, P. Schmidtová, S. Balloccu, O. Dušek
INLG 2024 (demo)
ReproHum #0043-4: Evaluating Summarization Models — Impact of Education and Language Proficiency on Reproducibility
M. Lango, P. Schmidtová, S. Balloccu, O. Dušek
4th Workshop on Human Evaluation of NLP Systems (HumEval), 2024
THEaiTRE: Generating Theatre Play Scripts Using Artificial Intelligence
P. Schmidtová
Thesis, Institute of Formal and Applied Linguistics, 2024
Faithfulness of Natural Language Generation
P. Schmidtová
20th Young Researchers' Roundtable on Spoken Dialogue Systems (YRRSDS), 2024
2022–2023
GPT-2-Based Human-in-the-Loop Theatre Play Script Generation
R. Rosa, P. Schmidtová, O. Dušek, T. Musil, D. Mareček, S. Obaid, M. Nováková, K. Vosecká, J. Doležal
4th Workshop on Narrative Understanding (WNU2022), pp. 29–37
Three Ways of Using Large Language Models to Evaluate Chat
O. Plátek, V. Hudeček, P. Schmidtová, M. Lango, O. Dušek
DSTC 2023
Dialoguescript: Using Dialogue Agents to Produce a Script
P. Schmidtová, D. Javorský, C. Mikláš, T. Musil, R. Rosa, O. Dušek
arXiv:2206.08425, 2022
Semantic Accuracy in Natural Language Generation: A Thesis Proposal
P. Schmidtová
ACL Student Research Workshop, 2023
2020–2021
THEaiTRE 1.0: Interactive Generation of Theatre Play Scripts
R. Rosa, T. Musil, O. Dušek, D. Jurko, P. Schmidtová, D. Mareček, O. Bojar, T. Kocmi, D. Hrbek, D. Košťák, M. Kinská, M. Nováková, J. Doležal, K. Vosecká, T. Studeník, P. Žabka
arXiv:2102.08892, 2021
THEaiTRE: Artificial Intelligence to Write a Theatre Play
R. Rosa, O. Dušek, T. Kocmi, D. Mareček, T. Musil, P. Schmidtová, D. Jurko, O. Bojar, D. Hrbek, D. Košťák, M. Kinská, J. Doležal, K. Vosecká
arXiv:2006.14668, 2020
A Chatbot for the Banking Domain
P. Schmidtová
Bachelor's thesis, Charles University, 2019

Full list on Google Scholar.