---
title: "Marzieh Fadaee · Cohere — author profile and papers"
description: "Marzieh Fadaee, Cohere: 4 papers on Elamur Research (2017–2025), h-index 11 — affiliations, topics, co-authors and who cites them in our library."
canonical: "https://research.elamur.ai/free/en/authors/marzieh-fadaee/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/marzieh-fadaee/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Marzieh Fadaee

# Marzieh Fadaee

Marzieh Fadaee has 4 papers in our library, in 2017–2025, most of them on [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/), [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with [Beyza Ermis](https://md.research.elamur.ai/free/en/authors/beyza-ermis/), [Julia Kreutzer](https://md.research.elamur.ai/free/en/authors/julia-kreutzer/), [Sara Hooker](https://md.research.elamur.ai/free/en/authors/sara-hooker/).

4 papers in our library · 2017–2025

[OpenAlex](https://openalex.org/A5070153551) · [ORCID](https://orcid.org/0000-0002-4447-1213) · [Wikidata](https://www.wikidata.org/wiki/Q141203663) · [**h-index 11**](https://openalex.org/authors/A5070153551) · [62 works](https://openalex.org/works?filter=author.id:A5070153551) · [494 citations](https://openalex.org/works?filter=author.id:A5070153551&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/marzieh-fadaee/#papers) · [🔗 Cited 1,562 times in our library](https://md.research.elamur.ai/free/en/authors/marzieh-fadaee/cited-by/) · [5 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #3738](https://md.research.elamur.ai/free/en/paper-stars/page/38/#star-3738)

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

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Marzieh+Fadaee) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Marzieh+Fadaee) · [dblp](https://dblp.org/search?q=Marzieh+Fadaee) · [ACL Anthology](https://aclanthology.org/search/?q=Marzieh+Fadaee)

## Affiliations

[🏢**Cohere** San Francisco · United States 2024–2026 · 28 papers*current*](https://md.research.elamur.ai/free/en/companies/cohere/) · [🏢**Alpha Environmental** Emerson · United States 2022–2023 · 3 papers](https://ror.org/05j2afk93) · [🎓**University of Amsterdam** Amsterdam · Netherlands 2014–2021 · 3 papersEducation 2014–2019 · PhD, Informatics institute](https://md.research.elamur.ai/free/en/universities/university-of-amsterdam/) · [🎓**University of Tehran** Tehran · Iran 2010–2020 · 3 papersEducation 2010–2013 · MSc, Computer science](https://md.research.elamur.ai/free/en/universities/university-of-tehran/)

🏛️**Zeta Alpha** Amsterdam · [Netherlands](https://md.research.elamur.ai/free/en/countries/netherlands/) 2019Employment since 2019

[🎓**Sharif University of Technology** Tehran · Iran 2004–2009Education 2004–2009 · BSc, Computer science](https://md.research.elamur.ai/free/en/universities/sharif-university-of-technology/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

## Fields, topics and concepts

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

📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Language and Linguistics · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Safety Research · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/)

🧭 Topics 5 Research subjects and languages the work is about.[Multilingual & cross-lingual NLP · 3 works](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Low-resource languages · 1 work](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · [Machine translation · 1 work](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Bias, fairness & safety · 2 works](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/)

## Works by year

### 2020s

[**2025** 2 papers](https://md.research.elamur.ai/free/en/authors/marzieh-fadaee/year/2025/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/marzieh-fadaee/year/2024/)

### 2010s

[**2017** 1 paper](https://md.research.elamur.ai/free/en/authors/marzieh-fadaee/year/2017/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Data Augmentation for Low-Resource Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/fadaee-2017-data-augmentation-low-resource-neural/)** *(2017 · 425 citations)* Neural machine translation needs large parallel corpora. When data are scarce, words that appear only a few times end up with poorly learned representations. Borrowing the idea of data augmentation from computer vision, the authors introduce translation data augmentation (TDA), which builds extra training pairs by…
2. **[The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://md.research.elamur.ai/free/en/papers/aakanksha-2024-multilingual-alignment-prism-aligning-global/)** *(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…
3. **[M-RewardBench: Evaluating Reward Models in Multilingual Settings](https://md.research.elamur.ai/free/en/papers/gureja-2025-m-rewardbench-evaluating-reward-models/)** *(2025 · 28 citations)* Reward models (RMs) steer LLM alignment, but they are built and tested almost entirely in English. This paper asks how well RMs judge responses in other languages. The authors built M-RewardBench, a benchmark of about 2.87k preference instances spanning 23 typologically varied languages, including Ukrainian.
4. **[The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It](https://md.research.elamur.ai/free/en/papers/yong-2025-state-multilingual-llm-safety-research/)** *(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…

## All works

9 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. **[Data Augmentation for Low-Resource Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/fadaee-2017-data-augmentation-low-resource-neural/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Marzieh Fadaee, Arianna Bisazza, Christof Monz*2017 · 425 citations*
2. **[Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs ↗](https://aclanthology.org/2024.acl-long.662/) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Arash Ahmadian et al.*2024 · 217 citations*
3. **[Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation ↗](https://aclanthology.org/D18-1040/) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yet**Marzieh Fadaee, Christof Monz*2018 · 122 citations*
4. **[InPars: Data Augmentation for Information Retrieval using Large Language Models ↗](https://arxiv.org/abs/2202.05144) arXiv:2202.05144 · no summary yet**Luiz Bonifacio et al.*2022 · 72 citations*
5. **[The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://md.research.elamur.ai/free/en/papers/aakanksha-2024-multilingual-alignment-prism-aligning-global/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Aakanksha, Arash Ahmadian, Beyza Ermis, et al.*2024 · 49 citations*
6. **[M-RewardBench: Evaluating Reward Models in Multilingual Settings](https://md.research.elamur.ai/free/en/papers/gureja-2025-m-rewardbench-evaluating-reward-models/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Srishti Gureja, Lester James V. Miranda, Shayekh Bin Islam, et al.*2025 · 28 citations*
7. **[The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It](https://md.research.elamur.ai/free/en/papers/yong-2025-state-multilingual-llm-safety-research/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Zheng Xin Yong, Beyza Ermis, Marzieh Fadaee, et al.*2025 · 25 citations*
8. **[The Leaderboard Illusion ↗](https://arxiv.org/abs/2504.20879) arXiv:2504.20879 · no summary yet**Shivalika Singh et al.*2025 · 22 citations*
9. **[Déj\‘a Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation ↗](https://arxiv.org/abs/2504.11829) arXiv:2504.11829 · no summary yet**Julia Kreutzer et al.*2025 · 7 citations*

## Co-authors here

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

- [Beyza Ermis](https://md.research.elamur.ai/free/en/authors/beyza-ermis/) ×2
- [Julia Kreutzer](https://md.research.elamur.ai/free/en/authors/julia-kreutzer/) ×2
- [Sara Hooker](https://md.research.elamur.ai/free/en/authors/sara-hooker/) ×2
- [Arash Ahmadian](https://md.research.elamur.ai/free/en/authors/arash-ahmadian/)
- [Arianna Bisazza](https://md.research.elamur.ai/free/en/authors/arianna-bisazza/)
- [Christof Monz](https://md.research.elamur.ai/free/en/authors/christof-monz/)
- [Lester James V. Miranda](https://md.research.elamur.ai/free/en/authors/lester-james-v-miranda/)
- [Nathan Lambert](https://md.research.elamur.ai/free/en/authors/nathan-lambert/)
- [Rishabh Maheshwary](https://md.research.elamur.ai/free/en/authors/rishabh-maheshwary/)
- [Sebastian Ruder](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/)
- [Seraphina Goldfarb-Tarrant](https://md.research.elamur.ai/free/en/authors/seraphina-goldfarb-tarrant/)
- [Stephen H. Bach](https://md.research.elamur.ai/free/en/authors/stephen-h-bach/)

## Venues

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

- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×5: [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/), [ACL 2017](https://md.research.elamur.ai/free/en/venues/acl/2017/)
- [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ×3: [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/), [EMNLP 2024](https://md.research.elamur.ai/free/en/venues/emnlp/2024/)

## Cited by

Papers of our library cite their works 1,562 times (of the 149,439 papers whose bibliographies we read); [311 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/marzieh-fadaee/cited-by/).

Updated 30 October 2026