Vladimir Mikulik
Vladimir Mikulik has 2 papers in our library, in 2022–2023, most of them on Language models & pretraining, Interpretability; often with Geoffrey Irving, Francis Song, Jacob Menick.
OpenAlex · ORCID · h-index 9 · 23 works · 2,318 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 2,534 citations in our library · 3 more in our library without a page yet · ⭐ Paper Star rank #3637
Affiliations
🔬American Anthropological AssociationArlington ·
United States2026 · 1 paper🏛️Anthropological Survey of IndiaKolkata ·
India2026 · 1 paper🔬Laboratoire d'Anthropologie SocialeParis ·
France2026 · 1 paper🎓University of OxfordOxford ·
United Kingdom2019–2020 · 2 papers
Topics
Language models & pretraining (1) Interpretability (1)
Works by year
2020s
Papers
- Teaching language models to support answers with verified quotes (2022 · 211 citations)
Large language models frequently get fact-based queries right, but users cannot tell which claims to trust without checking them, because models can invent convincing falsehoods. - Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla (2023 · 51 citations)
Circuit analysis has mostly been demonstrated on small networks, such as two-layer attention-only transformers or the 117M GPT-2.
Also in our library
Co-authors here
- Geoffrey Irving ×2
- Francis Song
- Jacob Menick
- Janos Kramar
- John Aslanides
- Lucy Campbell-Gillingham
- Maja Trebacz
- Martin Chadwick
- Mia Glaese
- Nat McAleese
- Neel Nanda
- Rohin Shah
Cited by
This page in Markdown → https://md.research.elamur.ai/free/en/authors/vladimir-mikulik/