Elamur Research⌕
☰
home / authors / Mrinank Sharma

Mrinank Sharma

Mrinank Sharma has 2 papers in our library, in 2023–2025, most of them on Language models & pretraining, Bias, fairness & safety; often with Amanda Askell, Meg Tong, Cem Anil.

2 papers in our library · 2023–2025

OpenAlex · ORCID · Wikidata · h-index 11 · 37 works · 1,906 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 449 times in our library · 4 more in our library without a page yet · ⭐ Paper Stars ranking: #4276

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

🎓University of OxfordOxford · United Kingdom2019–2025 · 17 papers🏢AnthropicSan Francisco · United States2024–2026 · 2 papersEmployment until 2026

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 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workBias, fairness & safety · 1 work

 Works by year

2020s

20251 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Towards Understanding Sycophancy in Language Models (2023 · 384 citations)
    The paper looks at sycophancy: AI assistants telling users what they seem to want to hear instead of what is accurate.
  2. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming (2025 · 29 citations)
    The paper tackles universal jailbreaks: prompting strategies that consistently get past an LLM's safeguards across almost all queries in a domain. In the CBRN domain, such attacks could give non-experts step-by-step help with dangerous procedures.

All works

6 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. Towards Understanding Sycophancy in Language ModelsarXiv:2310.13548Mrinank Sharma, Meg Tong, Tomasz Korbak, et al.2023 · 384 citations
  2. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training ↗arXiv:2401.05566 · no summary yetEvan Hubinger et al.2024 · 123 citations
  3. Many-shot Jailbreaking ↗neural information processing systems · no summary yetCem Anil et al.2024 · 109 citations
  4. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingarXiv:2501.18837Mrinank Sharma, Meg Tong, Jesse Mu, et al.2025 · 29 citations
  5. Forecasting Rare Language Model Behaviors ↗arXiv (Cornell University) · no summary yetErik Jones et al.2025 · 3 citations
  6. Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks ↗arXiv (Cornell University) · no summary yetHoagy Cunningham et al.2026 · 2 citations

 Co-authors here

11 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 449 times (of the 149,439 papers whose bibliographies we read); 89 citing papers with a page here →.

Updated

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