Elamur Research⌕
☰
home / authors / Amr Sharaf

Amr Sharaf

Amr Sharaf has 2 papers in our library, in 2023–2024, most of them on Machine translation; often with Arul Menezes, Benjamin Van Durme, Hany Hassan Awadalla.

2 papers in our library · 2023–2024

OpenAlex · h-index 9 · 26 works · 446 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 583 times in our library · 1 more in our library without a page yet · ⭐ Paper Star rank #4132

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

🎓University of Maryland, College ParkCollege Park · United States2017–2021 · 8 papers🏢MicrosoftRedmond · United States2022–2023 · 2 papers🎓Alexandria UniversityAlexandria · Egypt2015 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 4 Artificial Intelligence · 2 works Arts and Humanities · 2 works Computer Science · 2 works Language and Linguistics · 2 works

🧭 Topics 1 Machine translation · 2 works

 Works by year

2020s

20241 paperContrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation20231 paperLeveraging GPT-4 for Automatic Translation Post-Editing

 Papers

The most cited first (OpenAlex and our library).

  1. Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation (2024 · 207 citations)
    Mid-sized LLMs (7B/13B) translate reasonably well but still trail GPT-4 and the strongest WMT systems. The authors trace part of this gap to supervised fine-tuning (SFT). SFT copies reference translations, so the model can only be as good as those references. It also never teaches the model to avoid output that is…
  2. Leveraging GPT-4 for Automatic Translation Post-Editing (2023 · 107 citations)
    Even strong NMT systems sometimes produce badly broken output, so translations used in high-stakes settings still need post-editing.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation · original ↗ · no summary yet · arXiv:2302.09210Amr Hendy et al.2023 · 525 citations
  2. Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine TranslationHaoran Xu, Amr Sharaf, Yunmo Chen, et al.arXiv:2401.08417 · 207 citations
  3. Leveraging GPT-4 for Automatic Translation Post-EditingVikas Raunak, Amr Sharaf, Yiren Wang, et al.Findings of the Association for Computational Linguistics · 107 citations

 Co-authors here

10 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 583 times (of the 141,840 papers whose bibliographies we read); 62 citing papers with a page here →.

Updated

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