--- title: "Carson Denison — author profile and papers · Reasoning" description: "Carson Denison: 3 papers on Elamur Research (2023–2025), h-index 8 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/carson-denison/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/carson-denison/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Carson Denison # Carson Denison Carson Denison has 3 papers in our library, in 2023–2025, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/); often with [Ansh Radhakrishnan](https://md.research.elamur.ai/free/en/authors/ansh-radhakrishnan/), [Evan Hubinger](https://md.research.elamur.ai/free/en/authors/evan-hubinger/), [Tamera Lanham](https://md.research.elamur.ai/free/en/authors/tamera-lanham/). 3 papers in our library · 2023–2025 [OpenAlex](https://openalex.org/A5079864698) · [**h-index 8**](https://openalex.org/authors/A5079864698) · [11 works](https://openalex.org/works?filter=author.id:A5079864698) · [328 citations](https://openalex.org/works?filter=author.id:A5079864698&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/carson-denison/#papers) · [🔗 Cited 665 times in our library](https://md.research.elamur.ai/free/en/authors/carson-denison/cited-by/) · [5 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #4283](https://md.research.elamur.ai/free/en/paper-stars/page/43/#star-4283) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Carson+Denison) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Carson+Denison) · [dblp](https://dblp.org/search?q=Carson+Denison) · [ACL Anthology](https://aclanthology.org/search/?q=Carson+Denison) ## Affiliations [🎓**University of Oxford** Oxford · United Kingdom 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Safety Research · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 2 Research subjects and languages the work is about.[Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) ## Works by year ### 2020s [**2025** 1 paper](https://md.research.elamur.ai/free/en/authors/carson-denison/year/2025/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/carson-denison/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/carson-denison/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Measuring Faithfulness in Chain-of-Thought Reasoning](https://md.research.elamur.ai/free/en/papers/lanham-2023-measuring-faithfulness-chain-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](https://md.research.elamur.ai/free/en/papers/hubinger-2024-sleeper-agents-training-deceptive-llms/)** *(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. **[Reasoning Models Don't Always Say What They Think](https://md.research.elamur.ai/free/en/papers/chen-2025-reasoning-models-don-t-always/)** *(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… ## All works 8 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. [**Measuring Faithfulness in Chain-of-Thought Reasoning arXiv:2307.13702**Tamera Lanham, Anna Chen, Ansh Radhakrishnan, et al.*2023 · 262 citations*](https://md.research.elamur.ai/free/en/papers/lanham-2023-measuring-faithfulness-chain-thought-reasoning/) 2. [**Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training arXiv:2401.05566**Evan Hubinger, Carson Denison, Jesse Mu, et al.*2024 · 123 citations*](https://md.research.elamur.ai/free/en/papers/hubinger-2024-sleeper-agents-training-deceptive-llms/) 3. **[Many-shot Jailbreaking ↗](https://doi.org/10.52202/079017-4121) neural information processing systems · no summary yet**Cem Anil et al.*2024 · 109 citations* 4. [**Reasoning Models Don't Always Say What They Think arXiv:2505.05410**Yanda Chen, Joe Benton, Ansh Radhakrishnan, et al.*2025 · 106 citations*](https://md.research.elamur.ai/free/en/papers/chen-2025-reasoning-models-don-t-always/) 5. **[Alignment faking in large language models ↗](https://arxiv.org/abs/2412.14093) arXiv (Cornell University) · no summary yet**Ryan Greenblatt et al.*2024 · 82 citations* 6. **[Question Decomposition Improves the Faithfulness of Model-Generated Reasoning ↗](https://arxiv.org/abs/2307.11768) arXiv (Cornell University) · no summary yet**Ansh Radhakrishnan et al.*2023 · 74 citations* 7. **[Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models ↗](https://arxiv.org/abs/2406.10162) arXiv (Cornell University) · no summary yet**Carson Denison et al.*2024 · 46 citations* 8. **[Auditing language models for hidden objectives ↗](https://arxiv.org/abs/2503.10965) arXiv (Cornell University) · no summary yet**Marks, Samuel et al.*2025 · 19 citations* ## Co-authors here 12 of 22 co-authors with a page, the most papers together first. - [Ansh Radhakrishnan](https://md.research.elamur.ai/free/en/authors/ansh-radhakrishnan/) ×2 - [Evan Hubinger](https://md.research.elamur.ai/free/en/authors/evan-hubinger/) ×2 - [Tamera Lanham](https://md.research.elamur.ai/free/en/authors/tamera-lanham/) ×2 - [Amanda Askell](https://md.research.elamur.ai/free/en/authors/amanda-askell/) - [Anna Chen](https://md.research.elamur.ai/free/en/authors/anna-chen/) - [Benoit Steiner](https://md.research.elamur.ai/free/en/authors/benoit-steiner/) - [Daniel M. Ziegler](https://md.research.elamur.ai/free/en/authors/daniel-m-ziegler/) - [Danny Hernandez](https://md.research.elamur.ai/free/en/authors/danny-hernandez/) - [Dustin Li](https://md.research.elamur.ai/free/en/authors/dustin-li/) - [Esin Durmus](https://md.research.elamur.ai/free/en/authors/esin-durmus/) - [Jackson Kernion](https://md.research.elamur.ai/free/en/authors/jackson-kernion/) - [Jesse Mu](https://md.research.elamur.ai/free/en/authors/jesse-mu/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - neural information processing systems ## Cited by Papers of our library cite their works 665 times (of the 149,439 papers whose bibliographies we read); [136 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/carson-denison/cited-by/). Updated 2 November 2026