Elamur Research⌕
☰
home / authors / Beyza Ermis

Beyza Ermis

Beyza Ermis has 4 papers in our library, in 2024–2026, most of them on Multilingual & cross-lingual NLP, Bias, fairness & safety, Language models & pretraining; often with Julia Kreutzer, Marzieh Fadaee, Sara Hooker.

4 papers in our library · 2024–2026

OpenAlex · h-index 11 · 51 works · 435 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 445 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7017

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢CohereSan Francisco · United States2024–2026 · 15 paperscurrent🎓Boğaziçi UniversityIstanbul · Türkiye2012–2019 · 10 papers🏢AmazonSeattle · United States2018–2021 · 2 papers🏢AmazonBerlin · Germany2020 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 4 worksArts and Humanities · 4 worksComputer Science · 4 worksLanguage and Linguistics · 4 worksSafety Research · 2 worksSocial Sciences · 2 works

🧭 Topics 4Research subjects and languages the work is about.Multilingual & cross-lingual NLP · 3 worksBias, fairness & safety · 2 worksLanguage models & pretraining · 1 workReasoning · 1 work

 Works by year

2020s

20261 paper20251 paper20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm (2024 · 49 citations)
    Most LLM safety alignment targets English and relies on Western-centric data. This leaves non-English users more exposed and lets other languages serve as a route around guardrails. The paper asks three things: whether harm mitigation can work across many languages at once, whether it transfers across languages, and…
  2. The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It (2025 · 25 citations)
    This survey examines how much LLM safety research covers languages other than English. The authors reviewed nearly 300 papers from 2020–2024 published at ∗ACL conferences and workshops. They found candidate papers by searching abstracts for "safe" and "safety". They then labeled each paper by hand with a safety…
  3. Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress (2024 · 12 citations)
    Synthetic training data for LLMs usually comes from one "teacher" model. That approach can pass on the teacher's biases, contribute to model collapse, and fail in multilingual work, where no single model is strongest in every language. The authors propose multilingual arbitrage : each prompt is sent to whichever…
  4. Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection (2026 · 1 citation)
    Fine-tuning LLMs for Natural Language Inference (NLI) raises in-distribution accuracy but often lowers out-of-distribution (OOD) accuracy.

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce HarmConference on Empirical Methods in Natural Language Processing (EMNLP)Aakanksha, Arash Ahmadian, Beyza Ermis, et al.2024 · 49 citations
  2. The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating ItConference on Empirical Methods in Natural Language Processing (EMNLP)Zheng Xin Yong, Beyza Ermis, Marzieh Fadaee, et al.2025 · 25 citations
  3. The Leaderboard Illusion ↗arXiv:2504.20879 · no summary yetShivalika Singh et al.2025 · 22 citations
  4. Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual ProgressarXiv:2408.14960Ayomide Odumakinde, Daniel D'souza, Pat Verga, et al.2024 · 12 citations
  5. Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data SelectionFindings of the Association for Computational LinguisticsJoe Stacey, Lisa Alazraki, Aran Ubhi, et al.2026 · 1 citation

 Co-authors here

12 of 13 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 445 times (of the 149,439 papers whose bibliographies we read); 110 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/beyza-ermis/