Publications | Esra Dönmez

^* denotes equal contribution.

2026

SEAL: SocioEconomic Alignment in LLMs

Elisa Bassignana^*, Lorena Calvo-Bartolomé^*, Esra Dönmez^*, and 4 more authors

In Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI), Oct 2026

alignmentsocioeconomic statussociotechnical alignment

@inproceedings{bassignana-etal-2026-seal,
  title = {{SEAL}: {S}ocio{E}conomic {A}lignment in {LLM}s},
  author = {Bassignana, Elisa and Calvo-Bartolom{\'e}, Lorena and D{\"o}nmez, Esra and Lutz, Marlene and Muti, Arianna and Neplenbroek, Vera and Rooein, Donya},
  booktitle = {Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)},
  month = oct,
  year = {2026},
  address = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics}
}

Structuring the Space of Sociotechnical Alignment

Esra Dönmez and Agnieszka Falenska

Jul 2026

Preprint alignmentsurveyliterature reviewframeworksociotechnical alignment

arXiv Bib Website

@misc{donmez-falenska-2026-structuring,
  title = {Structuring the Space of Sociotechnical Alignment},
  author = {D{\"o}nmez, Esra and Falenska, Agnieszka},
  year = {2026},
  month = jul,
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2607.01250},
}

A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models

Yassir El Attar, Esra Dönmez, Maximilian Maurer, and 1 more author

In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2026, Nov 2026

AI text detection

arXiv Bib

@inproceedings{el-attar-etal-2026-systematic,
  title = {A Systematic Analysis of Linguistic Features in {AI}-Generated Text Detection Across Domains and Models},
  author = {El Attar, Yassir and D{\"o}nmez, Esra and Maurer, Maximilian and Falenska, Agnieszka},
  booktitle = {Findings of the Association for Computational Linguistics: AACL-IJCNLP 2026},
  month = nov,
  year = {2026},
  address = {Hengqin, China},
  publisher = {Association for Computational Linguistics},
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2606.04177}
}

Leveraging Comparable Toxicity Lexicons in Prompt Instructions for Multilingual Text Detoxification

Yassir El Attar, Esra Dönmez, Nina K. Ohlendorf, and 1 more author

In Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC), May 2026

toxicity

DOI Bib

@inproceedings{el-attar-etal-2026-leveraging,
  title = {Leveraging Comparable Toxicity Lexicons in Prompt Instructions for Multilingual Text Detoxification},
  author = {El Attar, Yassir and D{\"o}nmez, Esra and Ohlendorf, Nina K. and Falenska, Agnieszka},
  editor = {Rapp, Reinhard and Terryn, Ayla Rigouts and Sharoff, Serge and Zweigenbaum, Pierre},
  booktitle = {Proceedings of the 19th Workshop on Building and Using Comparable Corpora ({BUCC})},
  month = may,
  year = {2026},
  address = {Palma de Mallorca, Spain},
  publisher = {ELRA Language Resources Association (ELRA)},
  url = {https://aclanthology.org/2026.bucc-1.12/},
  doi = {10.63317/2f5i2922qqe2},
  pages = {108--118}
}

Better Reward Models Are Not Less Biased Ones: Social Alignment Beyond Standard Reward Benchmarks

Gayane Ghazaryan and Esra Dönmez

May 2026

Preprint alignmentreward modelssocial alignmentbenchmark

arXiv Bib

@misc{ghazaryan-donmez-2026-misaligned,
  title = {Better Reward Models Are Not Less Biased Ones: Social Alignment Beyond Standard Reward Benchmarks},
  author = {Ghazaryan, Gayane and D{\"o}nmez, Esra},
  year = {2026},
  month = may,
  archiveprefix = {arXiv},
  url = {https://arxiv.org/abs/2605.05003}
}

2025

“I understand your perspective”: LLM Persuasion through the Lens of Communicative Action Theory

Esra Dönmez and Agnieszka Falenska

In Findings of the Association for Computational Linguistics: ACL 2025, Jul 2025

persuasionsycophancy

DOI Bib

@inproceedings{donmez-falenska-2025-understand,
  title = {``{I} understand your perspective'': {LLM} Persuasion through the Lens of Communicative Action Theory},
  author = {D{\"o}nmez, Esra and Falenska, Agnieszka},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
  month = jul,
  year = {2025},
  address = {Vienna, Austria},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.findings-acl.793/},
  doi = {10.18653/v1/2025.findings-acl.793},
  pages = {15312--15327},
  isbn = {979-8-89176-256-5}
}

AI Argues Differently: Distinct Argumentative and Linguistic Patterns of LLMs in Persuasive Contexts

Esra Dönmez^*, Maximilian Maurer^*, Gabriella Lapesa, and 1 more author

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025

persuasionlinguistic convergenceargumentation

DOI Bib

@inproceedings{donmez-etal-2025-ai,
  title = {{AI} Argues Differently: Distinct Argumentative and Linguistic Patterns of {LLM}s in Persuasive Contexts},
  author = {D{\"o}nmez, Esra and Maurer, Maximilian and Lapesa, Gabriella and Falenska, Agnieszka},
  editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  month = nov,
  year = {2025},
  address = {Suzhou, China},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.emnlp-main.1755/},
  doi = {10.18653/v1/2025.emnlp-main.1755},
  pages = {34595--34626},
  isbn = {979-8-89176-332-6}
}

2024

Please note that I’m just an AI: Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech Identification

Esra Dönmez, Thang Vu, and Agnieszka Falenska

In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024

offensive languageerroneous generationstereotypes

DOI Bib

@inproceedings{donmez-etal-2024-please,
  title = {Please note that {I}{'}m just an {AI}: Analysis of Behavior Patterns of {LLM}s in (Non-)offensive Speech Identification},
  author = {D{\"o}nmez, Esra and Vu, Thang and Falenska, Agnieszka},
  editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
  month = nov,
  year = {2024},
  address = {Miami, Florida, USA},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.emnlp-main.1019/},
  doi = {10.18653/v1/2024.emnlp-main.1019},
  pages = {18340--18357}
}

2023

HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities

Esra Dönmez^*, Pascal Tilli^*, Hsiu-Yu Yang^*, and 2 more authors

In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), Dec 2023

vision & languageimage–text matchingmisalignmentcounterfactuals

DOI Bib

@inproceedings{donmez-etal-2023-hnc,
  title = {{HNC}: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities},
  author = {D{\"o}nmez, Esra and Tilli, Pascal and Yang, Hsiu-Yu and Vu, Thang and Silberer, Carina},
  editor = {Jiang, Jing and Reitter, David and Deng, Shumin},
  booktitle = {Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)},
  month = dec,
  year = {2023},
  address = {Singapore},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2023.conll-1.24/},
  doi = {10.18653/v1/2023.conll-1.24},
  pages = {364--388}
}