--- title: "Soheil Feizi — author profile and papers" description: "Soheil Feizi, Mohamed bin Zayed University of Artificial Intelligence: 2 papers on Elamur Research (2023), h-index 30 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/soheil-feizi/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/soheil-feizi/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Soheil Feizi # Soheil Feizi 2 papers on this site · 2023 current affiliation [Mohamed bin Zayed University of Artificial Intelligence](https://ror.org/0258gkt32), Abu Dhabi, United Arab Emirates; [University of Maryland, College Park](https://ror.org/047s2c258), College Park, United States Soheil Feizi has 2 papers on this site, in 2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/); often with [Aounon Kumar](https://md.research.elamur.ai/free/en/authors/aounon-kumar/). [OpenAlex](https://openalex.org/A5025450606) · [ORCID](https://orcid.org/0000-0003-0944-8242) · [**h-index 30**](https://openalex.org/authors/A5025450606) · [198 works](https://openalex.org/works?filter=author.id:A5025450606) · [9 875 citations](https://openalex.org/works?filter=author.id:A5025450606&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/soheil-feizi/#papers) · [234 citations in our library](https://md.research.elamur.ai/free/en/authors/soheil-feizi/cited-by/) · 2 more works in our library 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=Soheil+Feizi) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Soheil+Feizi) · [dblp](https://dblp.org/search?q=Soheil+Feizi) · [ACL Anthology](https://aclanthology.org/search/?q=Soheil+Feizi) ## Affiliations - [University of Maryland, College Park](https://ror.org/047s2c258) · College Park, United States —current · 2017–2026 on 122 papers · employment (Wikidata) - [Mohamed bin Zayed University of Artificial Intelligence](https://ror.org/0258gkt32) · Abu Dhabi, United Arab Emirates —current · 2026 on 2 papers - [Massachusetts Institute of Technology](https://ror.org/042nb2s44) · Cambridge, United States —2009–2018 on 25 papers · education (Wikidata) - [Broad Institute](https://ror.org/05a0ya142) · Cambridge, United States —2012–2018 on 6 papers - [MIT Computer Science and Artificial Intelligence Laboratory](https://ror.org/01e85r662) · Cambridge, United States —2012–2018 on 5 papers - [Stanford University](https://ror.org/00f54p054) · Stanford, United States —2017–2018 on 3 papers · employment (Wikidata) - [Sharif University of Technology](https://ror.org/024c2fq17) · Tehran, Iran —2007–2009 on 7 papers · education (Wikidata) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [Bias, fairness & safety 1](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) ## Papers The most cited first (OpenAlex and our library). 1. **[Can AI-Generated Text be Reliably Detected?](https://md.research.elamur.ai/free/en/papers/sadasivan-2023-ai-generated-text-reliably-detected/)** *(2023 · 301 citations)* The paper tests whether current detectors of machine-written text still work when someone deliberately tries to fool them. 2. **[Certifying LLM Safety against Adversarial Prompting](https://md.research.elamur.ai/free/en/papers/kumar-2023-certifying-llm-safety-against-adversarial/)** *(2023 · 110 citations)* Safety-aligned LLMs can still be jailbroken when an attacker attaches crafted adversarial tokens to a harmful request. ## Also in our library 2 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 1 co-author with a page, the most papers together first. - [Aounon Kumar](https://md.research.elamur.ai/free/en/authors/aounon-kumar/) ×2 ## Cited by Papers of our library cite their works 234 times (of the 140 884 papers whose bibliographies we read); [20 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/soheil-feizi/cited-by/).