Elamur Research⌕
☰
home / authors / Fabien Roger

Fabien Roger

Fabien Roger has 2 papers in our library, in 2023–2025, most of them on Reasoning, Language models & pretraining; often with Ansh Radhakrishnan, Carson Denison, John Schulman.

2 papers in our library · 2023–2025

OpenAlex · h-index 4 · 25 works · 57 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 172 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #8045

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

🏢AnthropicSan Francisco · United States2025–2026 · 5 paperscurrent🔬American Anthropological AssociationArlington · United States2026 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksComputer Science · 2 worksSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 2 worksLanguage models & pretraining · 1 work

 Works by year

2020s

20251 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Reasoning Models Don't Always Say What They Think (2025 · 106 citations)
    Monitoring a model's chain-of-thought (CoT) is often proposed as a safety tool. It only works if the written reasoning reflects what actually drives the answer. The authors examine this using Claude 3.7 Sonnet and DeepSeek R1, both of which perform explicit reasoning, and set them against the non-reasoning Claude 3.5…
  2. Preventing Language Models From Hiding Their Reasoning (2023 · 10 citations)
    Chain-of-thought (CoT) is only useful for overseeing an LLM if the written steps match what the model actually computes.

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. Reasoning Models Don't Always Say What They ThinkarXiv:2505.05410Yanda Chen, Joe Benton, Ansh Radhakrishnan, et al.2025 · 106 citations
  2. Alignment faking in large language models ↗arXiv (Cornell University) · no summary yetRyan Greenblatt et al.2024 · 82 citations
  3. Auditing language models for hidden objectives ↗arXiv (Cornell University) · no summary yetMarks, Samuel et al.2025 · 19 citations
  4. Preventing Language Models From Hiding Their ReasoningarXiv:2310.18512Fabien Roger, Ryan Greenblatt2023 · 10 citations
  5. Quantifying Elicitation of Latent Capabilities in Language Models ↗neural information processing systems · no summary yetElizabeth Donoway et al.2025 · 1 citation

 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 172 times (of the 149,439 papers whose bibliographies we read); 41 citing papers with a page here →.

Updated

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