Elamur Research⌕
☰
home / authors / Ekdeep Singh Lubana

Ekdeep Singh Lubana

Ekdeep Singh Lubana has 2 papers in our library, in 2026, most of them on Interpretability; often with Aaron Mueller.

2 papers in our library · 2026

OpenAlex · ORCID · h-index 7 · 67 works · 164 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 70 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #11962

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

🏢Precision ResearchDes Plaines · United States2026 · 1 papercurrent🎓University of MichiganAnn Arbor · United States2019–2024 · 11 papers🎓Harvard UniversityCambridge · United States2023–2025 · 10 papers🎓Indian Institute of Technology RoorkeeRoorkee · India2018–2019 · 3 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.

 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 worksComputer Science · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 workSafety Research · 1 workSocial Sciences · 1 work

🧭 Topics 1Research subjects and languages the work is about.Interpretability · 1 work

 Works by year

2020s

20262 papers

 Papers

The most cited first (OpenAlex and our library).

  1. From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? (2026)
    Interpretability research usually judges featurizers such as sparse autoencoders (SAEs) and probes one concept at a time, implicitly assuming that concepts are independent.
  2. The Impact of Off-Policy Training Data on Probe Generalisation (2026)
    Activation probes are a cheap way to flag worrying behaviour in LLMs at inference time. However, natural labelled examples of behaviours like deception are scarce, so probes are often trained on synthetic or externally written responses. Skapars et al. test how much this matters. They compare four ways of producing…

All works

4 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. Foundational Challenges in Assuring Alignment and Safety of Large Language Models ↗arXiv:2404.09932 · no summary yetUsman Anwar et al.2024 · 87 citations
  2. From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?Annual Meeting of the Association for Computational Linguistics (ACL)Aaron Mueller, Andrew Lee, Shruti Joshi, et al.2026
  3. The Impact of Off-Policy Training Data on Probe GeneralisationFindings of the Association for Computational LinguisticsAdrians Skapars, Nathalie Maria Kirch, Samuel Dower, et al.2026
  4. Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention ↗arXiv (Cornell University) · no summary yetJing Huang et al.2026

 Co-authors here

1 co-author 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 70 times (of the 149,439 papers whose bibliographies we read); 14 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ekdeep-singh-lubana/