Elamur Research⌕
☰
home / authors / Kanishk Gandhi

Kanishk Gandhi

Kanishk Gandhi has 3 papers in our library, in 2024–2025, most of them on Language models & pretraining; often with Noah D. Goodman, Anikait Singh, Emma Brunskill.

3 papers in our library · 2024–2025

OpenAlex · h-index 6 · 29 works · 122 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 352 times in our library · 8 more in our library without a page yet · ⭐ Paper Stars ranking: #6185

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

🎓Stanford UniversityStanford · United States2022–2026 · 17 paperscurrent🎓New York UniversityNew York · United States2019–2021 · 2 papers

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 · 3 worksComputer Science · 3 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksDecision Sciences · 1 workManagement Science and Operations Research · 1 work

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work

 Works by year

2020s

20251 paper20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs (2025 · 123 citations)
    Why do some base language models gain a lot from reinforcement learning on verifiable tasks while others stall? The authors observe that Qwen-2.5-3B improves sharply on the Countdown arithmetic puzzle under a given RL setup, while Llama-3.2-3B, trained the same way, barely moves.
  2. Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels (2024 · 16 citations)
    Teaching a language model to respect a set of behavioral rules (a "constitution") usually depends on human preference labels, curated demonstrations, or reward models with reinforcement learning.
  3. Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models (2024 · 12 citations)
    Language models are increasingly used to stand in for human populations, for example when designing educational materials.

All works

11 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. Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRsarXiv:2503.01307Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, et al.2025 · 123 citations
  2. Stream of Search (SoS): Learning to Search in Language ↗arXiv:2404.03683 · no summary yetKanishk Gandhi et al.2024 · 49 citations
  3. Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought ↗arXiv:2501.04682 · no summary yetViolet Xiang et al.2025 · 47 citations
  4. Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models ↗arXiv:2502.17387 · no summary yetAlon Albalak et al.2025 · 43 citations
  5. Strategic Reasoning with Language Models ↗arXiv:2305.19165 · no summary yetKanishk Gandhi, Dorsa Sadigh, Noah D. Goodman2023 · 40 citations
  6. Certified Deductive Reasoning with Language Models ↗arXiv:2306.04031 · no summary yetGabriel Poesia et al.2023 · 23 citations
  7. Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models ↗arXiv:2412.02980 · no summary yetAlex Havrilla et al.2024 · 17 citations
  8. Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference LabelsConference on Neural Information Processing Systems (NeurIPS)Jan-Philipp Franken, Eric Zelikman, Rafael Rafailov, et al.2024 · 16 citations
  9. Psychometric Alignment: Capturing Human Knowledge Distributions via Language ModelsarXiv:2407.15645Joy He-Yueya, Wanjing Anya Ma, Kanishk Gandhi, et al.2024 · 12 citations
  10. BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery ↗arXiv:2501.01540 · no summary yetKanishk Gandhi et al.2025 · 4 citations
  11. Learning Next Action Predictors from Human-Computer Interaction ↗arXiv (Cornell University) · no summary yetOmar Shaikh et al.2026 · 3 citations

 Co-authors here

7 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 352 times (of the 149,439 papers whose bibliographies we read); 68 citing papers with a page here →.

Updated

↑ back to top

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