Leon Derczynski

Nvidia (United States) — United States

Computer Science · Physical Sciences

29h-index5.2kcitations185works2.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(83), Natural Language Processing Techniques(76), Semantic Web and Ontologies(27), Misinformation and Its Impacts(21), Hate Speech and Cyberbullying Detection(16)

Publications182 total

NLP Security and Ethics, in the Wild
Research Portal (King's College London)·2025Open Access
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
arXiv (Cornell University)·2025Open Access
Efficient Methods for Natural Language Processing: A Survey
UNC Libraries·2025Open Access
Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities
arXiv (Cornell University)·2025· 1 citedOpen Access
Summon a demon and bind it: A grounded theory of LLM red teaming
PLoS ONE·2025· 4 citedOpen Access
NLP Security and Ethics, in the Wild
Transactions of the Association for Computational Linguistics·2025Open Access
Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications
2025· 2 citedOpen Access
Nemotron-4 340B Technical Report
arXiv (Cornell University)·2024· 6 citedOpen Access
garak: A Framework for Security Probing Large Language Models
arXiv (Cornell University)·2024· 5 citedOpen Access
Introducing v0.5 of the AI Safety Benchmark from MLCommons
arXiv (Cornell University)·2024· 5 citedOpen Access
Countering Hateful and Offensive Speech Online - Open Challenges
2024· 2 citedOpen Access
Combating Security and Privacy Issues in the Era of Large Language Models
2024· 6 citedOpen Access
Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming
2023· 2 citedOpen Access
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
arXiv (Cornell University)·2023· 1 citedOpen Access
Assessing Language Model Deployment with Risk Cards
arXiv (Cornell University)·2023· 11 citedOpen Access
Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification
2023· 1 citedOpen Access
Efficient Methods for Natural Language Processing: A Survey
Transactions of the Association for Computational Linguistics·2023· 77 citedOpen Access
TeamAmpa at SemEval-2023 Task 3: Exploring Multilabel and Multilingual RoBERTa Models for Persuasion and Framing Detection
2023· 3 citedOpen Access
RWKV: Reinventing RNNs for the Transformer Era
2023· 268 citedOpen Access
Foreword to NEJLT Volume 8, 2022
Northern European Journal of Language Technology·2022Open Access
page 1 of 10Next →

Frequent Co-authors

Kalina Bontcheva(17), Maria Liakata(5), Arkaitz Zubiaga(5), Robert Gaizauskas(5), Marc Verhagen(4), James Pustejovsky(4), Marcos Zampieri(3), Preslav Nakov(3), Pepa Atanasova(3), Georgi Karadzhov(3), Hamdy Mubarak(3), Zeses Pitenis(3), Çağrı Çöltekin(3), Héctor Llorens(3), Genevieve Gorrell(3), Rob Procter(3), Ian Roberts(3), Sara Rosenthal(2), Naushad UzZaman(2), James F. Allen(2)