Elamur Research⌕
☰
home / authors / Irene Solaiman

Irene Solaiman

Irene Solaiman has 2 papers in our library, in 2019–2021, most of them on Language models & pretraining; often with Alec Radford, Amanda Askell, Ariel Herbert-Voss.

2 papers in our library · 2019–2021

OpenAlex · ORCID · Wikidata · h-index 7 · 13 works · 1,387 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 1,699 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #3471

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

🎓Iowa State UniversityAmes · United States2026 · 1 papercurrent🏢Hugging FaceNew York · United States2023–2025 · 2 papersEmployment · Policy Director

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

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 2 works

 Works by year

2020s

20211 paper

2010s

20191 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Release Strategies and the Social Impacts of Language Models (2019 · 554 citations)
    The report asks how a lab should publish a strong text generator whose output could feed fake news, impersonation or automated abuse, without giving up its benefits.
  2. Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets (2021 · 136 citations)
    Large pretrained language models such as GPT-3 can produce biased, toxic, or culturally inappropriate text. Retraining them from scratch for every desired behaviour is impractical, so the authors propose PALMS. PALMS is an iterative recipe for steering a pretrained model toward a chosen set of values. The steps are:

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. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model ↗arXiv:2211.05100 · no summary yetBigScience Workshop et al.2022 · 1,606 citations
  2. Release Strategies and the Social Impacts of Language ModelsarXiv:1908.09203Irene Solaiman, Miles Brundage, Jack Clark, et al.2019 · 554 citations
  3. Process for Adapting Language Models to Society (PALMS) with Values-Targeted DatasetsarXiv:2106.10328Irene Solaiman, Christy Dennison OpenAI)2021 · 136 citations

 Co-authors here

8 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 1,699 times (of the 149,439 papers whose bibliographies we read); 427 citing papers with a page here →.

Updated

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