Elamur Research⌕
☰
home / authors / David Duvenaud

David Duvenaud

David Duvenaud has 2 papers in our library, in 2019–2023, most of them on Language models & pretraining; often with Amanda Askell, Esin Durmus, Graeme Hirst.

2 papers in our library · 2019–2023

OpenAlex · h-index 40 · 101 works · 9,624 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 438 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #3284

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 TorontoToronto · Canada2016–2026 · 46 paperscurrent🎓University of British ColumbiaVancouver · Canada2008–2026 · 3 paperscurrent🔬Vector InstituteToronto · Canada2017–2023 · 14 papers🎓University of CambridgeCambridge · United Kingdom2011–2014 · 11 papers🎓Harvard UniversityCambridge · United States2015–2016 · 7 papers🎓University of OxfordOxford · United Kingdom2024 · 2 papers🏢GoogleMountain View · United States2020–2021 · 2 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.

 Concepts, shelves and topics

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

📚 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 · 1 work

 Works by year

2020s

20231 paperTowards Understanding Sycophancy in Language Models

2010s

20191 paperUnderstanding Undesirable Word Embedding Associations

 Papers

The most cited first (OpenAlex and our library).

  1. Towards Understanding Sycophancy in Language Models (2023 · 355 citations)
    The paper looks at sycophancy: AI assistants telling users what they seem to want to hear instead of what is accurate.
  2. Understanding Undesirable Word Embedding Associations (2019 · 171 citations)
    Word vectors are known to encode socially unwanted associations such as gender stereotypes, but the tools for detecting and removing them lack theoretical grounding.

All works

4 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. Convolutional Networks on Graphs for Learning Molecular FingerprintsarXiv:1509.09292 · original ↗ · no summary yetDavid Duvenaud et al.2015 · 940 citations
  2. Towards Understanding Sycophancy in Language ModelsarXiv:2310.13548Mrinank Sharma, Meg Tong, Tomasz Korbak, et al.2023 · 355 citations
  3. Understanding Undesirable Word Embedding AssociationsAnnual Meeting of the Association for Computational Linguistics (ACL)Kawin Ethayarajh, David Duvenaud, Graeme Hirst2019 · 171 citations
  4. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingarXiv:2401.05566 · original ↗ · no summary yetEvan Hubinger et al.2024 · 108 citations

 Co-authors here

7 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 438 times (of the 141,840 papers whose bibliographies we read); 35 citing papers with a page here →.

Updated

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