Elamur Research⌕
☰
home / authors / Koustuv Sinha

Koustuv Sinha

Koustuv Sinha has 2 papers in our library, in 2021, most of them on Language models & pretraining; often with Adina Williams, Joelle Pineau, Dieuwke Hupkes.

2 papers in our library · 2021

OpenAlex · ORCID · h-index 14 · 77 works · 1,229 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 180 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #3650

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

🎓McGill UniversityMontreal · Canada2018–2022 · 18 papers🔬Mila - Quebec Artificial Intelligence InstituteMontreal · Canada2018–2022 · 5 papers🏢MetaMenlo Park · United States2016–2022 · 3 papers🎓ETH ZurichZurich · Switzerland2023–2024 · 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 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

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

💡 Concepts 1Key ideas and methods explained on our concept pages.Distributional semantics · 1 work

 Works by year

2020s

20212 papersKoustuv Sinha's papers of 2021

 Papers

The most cited first (OpenAlex and our library).

  1. Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little (2021 · 292 citations)
    The paper asks why masked language model (MLM) pre-training works so well. One common view holds that models like BERT learn syntactic abstractions similar to a classical NLP pipeline. The authors test a different explanation: the benefit comes mainly from capturing higher-order word co-occurrence statistics.
  2. UnNatural Language Inference (2021 · 132 citations)
    This paper tests whether high-performing Natural Language Inference (NLI) models actually depend on word order, which is a basic requirement for "knowing syntax." The authors randomly shuffle the words of premise and hypothesis sentences and check whether models still output the original gold label.

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. Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for LittleKoustuv Sinha, Robin Jia, Dieuwke Hupkes, et al.Conference on Empirical Methods in Natural Language Processing (EMNLP) · 292 citations
  2. UnNatural Language InferenceKoustuv Sinha, Prasanna Parthasarathi, Joelle Pineau, et al.Annual Meeting of the Association for Computational Linguistics (ACL) · 132 citations
  3. Efficient Tool Use with Chain-of-Abstraction Reasoning · original ↗ · no summary yet · Proceedings of the 31st International Conference on Computational LinguisticsSilin Gao et al.2025 · 13 citations

 Co-authors here

5 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 180 times (of the 141,840 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/koustuv-sinha/