Elamur Research⌕
☰
home / authors / Alec Helyar

Alec Helyar

Alec Helyar has 2 papers in our library, in 2024, most of them on Reasoning, Bias, fairness & safety, Language models & pretraining; often with Adam Lerer, Adam Tauman Kalai, Ahmed El-Kishky.

2 papers in our library · 2024

OpenAlex · h-index 5 · 10 works · 120 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 1,874 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #1956

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

🏢OpenAISan Francisco · United States2025 · 2 paperscurrent🏢MicrosoftRedmond · United States2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 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 · 2 worksSocial Sciences · 2 works

🧭 Topics 3Research subjects and languages the work is about.Bias, fairness & safety · 2 worksReasoning · 2 worksLanguage models & pretraining · 1 work

 Works by year

2020s

20242 papersAlec Helyar's papers of 2024

 Papers

The most cited first (OpenAlex and our library).

  1. OpenAI o1 System Card (2024 · 1,065 citations)
    This system card describes how OpenAI evaluated the safety of its o1 reasoning models before release: o1 and o1-mini, a faster variant that is strong at coding.
  2. Deliberative Alignment: Reasoning Enables Safer Language Models (2024 · 109 citations)
    Conventional safety training (SFT, RLHF) has two weaknesses. LLMs answer instantly without deliberating, and they infer safety rules only indirectly from labeled examples. As a result, they can be jailbroken yet still refuse harmless requests. OpenAI researchers propose Deliberative Alignment, which teaches the model…

All works

3 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. OpenAI o1 System CardarXiv:2412.16720OpenAI, Aaron Jaech, Adam Kalai, et al.2024 · 1,065 citations
  2. Deliberative Alignment: Reasoning Enables Safer Language ModelsarXiv:2412.16339Melody Y. Guan, Manas Joglekar, Eric Wallace, et al.2024 · 109 citations
  3. A Framework for Automated Measurement of Responsible AI Harms in Generative AI Applications ↗arXiv:2310.17750 · no summary yetAhmed Magooda et al.2023 · 9 citations

 Co-authors here

12 of 13 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 1,874 times (of the 141,840 papers whose bibliographies we read); 93 citing papers with a page here →.

Updated

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