Elamur Research⌕
☰
home / authors / Dawn Drain

Dawn Drain

Dawn Drain has 2 papers in our library, in 2022–2023, most of them on Language models & pretraining, Interpretability, Bias, fairness & safety; often with Danny Hernandez, Amanda Askell, Anna Chen.

2 papers in our library · 2022–2023

OpenAlex · ORCID · h-index 19 · 28 works · 2,591 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 2,410 citations in our library · 4 more in our library without a page yet · ⭐ Paper Star rank #3751

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

🤝Machine Intelligence Research InstituteBerkeley · United States2022–2023 · 2 paperscurrent🏢MicrosoftRedmond · United States2020–2021 · 8 papers🏢AnthropicSan Francisco2021–2022 · 5 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.

 Topics

 Language models & pretraining (1) Interpretability (1) Bias, fairness & safety (1)

 Works by year

2020s

20231 paper20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. The Capacity for Moral Self-Correction in Large Language Models (2023 · 167 citations)
    The paper asks whether large dialogue models trained with RLHF can reduce their own biased or discriminatory outputs when simply asked to in plain language.
  2. Scaling Laws and Interpretability of Learning from Repeated Data (2022 · 62 citations)
    Large language models often see the same data several times. Sometimes this is done deliberately, to upweight high-quality sources, and sometimes it results from incomplete deduplication. The authors from Anthropic investigate why even a small fraction of repeated data harms models so severely. They train a family of…

Also in our library

4 more works of theirs are in our library without a page here yet; they will appear as we publish them.

 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 2,410 times (of the 140,884 papers whose bibliographies we read); 186 citing papers with a page here →.

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