🧑‍🔬 Iason Gabriel

🏛️ Affiliations

🏢Google DeepMindLondon · United Kingdom2017–2026 · 29 papersEmployment since 2017 · Staff Research Scientist, Ethics Research Teamcurrent🏢GoogleMountain View · United States2022–2026 · 4 paperscurrent🏢GoogleLondon · United Kingdom2025–2026 · 4 paperscurrent🎓School of Advanced StudyLondon · United Kingdom2025–2026 · 4 paperscurrent🎓University of LondonLondon · United Kingdom2025–2026 · 4 paperscurrent🎓University of OxfordOxford · United Kingdom2013–2024 · 5 papers

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.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Alignment of Language Agents (2021 · 120 citations)
   This DeepMind position paper asks how systems that act only by producing text, which the authors call language agents, can end up behaving against their designers' intentions.
2. Value Profiles for Encoding Human Variation (2025 · 15 citations)
   Annotators often disagree on subjective rating tasks such as toxicity, hate speech or chat preferences. This disagreement is usually discarded as noise. The authors instead model each rater individually and ask how a person is best represented. They propose value profiles: short free-text descriptions of a rater's…

All works

5 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. Scaling Language Models: Methods, Analysis & Insights from Training Gopher ↗arXiv:2112.11446 · no summary yetJack W. Rae et al.2021 · 928 citations
2. Alignment of Language AgentsarXiv:2103.14659Zachary Kenton, Tom Everitt, Laura Weidinger, et al.2021 · 120 citations
3. A Human Rights-Based Approach to Responsible AI ↗arXiv:2210.02667 · no summary yetVinodkumar Prabhakaran et al.2022 · 38 citations
4. Value Profiles for Encoding Human VariationConference on Empirical Methods in Natural Language Processing (EMNLP)Taylor Sorensen, Pushkar Mishra, Roma Patel, et al.2025 · 15 citations
5. Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights ↗arXiv:2502.19463 · no summary yetRafiya Javed et al.2025 · 2 citations

🤝 Co-authors here

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

• Geoffrey Irving
• Laura Weidinger
• Michael Henry Tessler
• Noah D. Goodman
• Pushkar Mishra
• Roma Patel
• Taylor Sorensen
• Tom Everitt
• Verena Rieser
• Vladimir Mikulik

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025

🔗 Cited by

Papers of our library cite their works 1,461 times (of the 149,439 papers whose bibliographies we read); 405 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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