🧑‍🔬 Evan Hubinger

🏛️ Affiliations

🏢AnthropicSan Francisco · United States2019–2026 · 5 paperscurrent🤝Machine Intelligence Research InstituteBerkeley · United States2019–2023 · 3 papers🎓University of OxfordOxford · United Kingdom2023–2024 · 2 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. Measuring Faithfulness in Chain-of-Thought Reasoning (2023 · 262 citations)
   Step-by-step "Chain-of-Thought" (CoT) prompting makes LLMs more accurate. It is less clear whether the written reasoning actually explains how the model reaches its answer. The authors, mostly at Anthropic, built a set of interventions to test this. They cut the CoT short, inserted an error into it, reworded it, or…
2. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (2024 · 123 citations)
   The paper asks whether an LLM that has learned a hidden, trigger-dependent harmful policy could be cleaned up by today's standard safety training.
3. Studying Large Language Model Generalization with Influence Functions (2023 · 105 citations)
   Knowing which training examples drive a given behavior in a large language model could help researchers anticipate and reduce its risks.

All works

10 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Steering Llama 2 via Contrastive Activation Addition ↗Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetNina Rimsky et al.2024 · 276 citations
2. Measuring Faithfulness in Chain-of-Thought ReasoningarXiv:2307.13702Tamera Lanham, Anna Chen, Ansh Radhakrishnan, et al.2023 · 262 citations
3. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingarXiv:2401.05566Evan Hubinger, Carson Denison, Jesse Mu, et al.2024 · 123 citations
4. Many-shot Jailbreaking ↗neural information processing systems · no summary yetCem Anil et al.2024 · 109 citations
5. Studying Large Language Model Generalization with Influence FunctionsarXiv:2308.03296Roger Grosse, Juhan Bae, Cem Anil, et al.2023 · 105 citations
6. Alignment faking in large language models ↗arXiv (Cornell University) · no summary yetRyan Greenblatt et al.2024 · 82 citations
7. Question Decomposition Improves the Faithfulness of Model-Generated Reasoning ↗arXiv (Cornell University) · no summary yetAnsh Radhakrishnan et al.2023 · 74 citations
8. Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models ↗arXiv (Cornell University) · no summary yetCarson Denison et al.2024 · 46 citations
9. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety ↗arXiv (Cornell University) · no summary yetTomek Korbak et al.2025 · 35 citations
10. Sabotage Evaluations for Frontier Models ↗arXiv (Cornell University) · no summary yetJoe Benton et al.2024 · 7 citations

🤝 Co-authors here

12 of 21 co-authors with a page, the most papers together first.

• Benoit Steiner ×2
• Carson Denison ×2
• Dustin Li ×2
• Esin Durmus ×2
• Kamile Lukošiute ×2
• Tamera Lanham ×2
• Alex Tamkin
• Amanda Askell
• Anna Chen
• Ansh Radhakrishnan
• Cem Anil
• Daniel M. Ziegler

Venues

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

• Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 1,174 times (of the 149,439 papers whose bibliographies we read); 297 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/evan-hubinger/