Elamur Research⌕
☰
home / authors / Manas Joglekar

Manas Joglekar

Manas Joglekar has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining, Reasoning, Bias, fairness & safety; often with Alec Helyar, Andrea Vallone, Boaz Barak.

2 papers in our library · 2023–2024

OpenAlex · ORCID · h-index 19 · 45 works · 1,057 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 1,450 times in our library · ⭐ Paper Stars ranking: #4324

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 · 1 papercurrent🎓Stanford UniversityStanford · United States2011–2017 · 26 papers🎓Indian Institute of Technology BombayMumbai · India2011–2012 · 3 papers🏢GoogleMountain View · United States2018 · 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.

 Concepts, shelves and topics

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

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksLanguage and Linguistics · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksMathematics · 1 workSafety Research · 1 workSocial Sciences · 1 work

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

 Works by year

2020s

20241 paperManas Joglekar's papers of 202420231 paperManas Joglekar's papers of 2023

 Papers

The most cited first (OpenAlex and our library).

  1. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision (2023 · 163 citations)
    Today's alignment methods, such as RLHF, assume humans can judge whether a model's outputs are good. That assumption may fail once models exceed human abilities. The OpenAI authors build a testable stand-in for this situation: a small "weak" model produces labels, and a much larger "strong" pretrained model is…
  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…

 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 1,450 times (of the 141,840 papers whose bibliographies we read); 69 citing papers with a page here →.

Updated

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