Author

Joshua Rozner

Observed names: Rozner, Josh, Rozner, Joshua

Institution: Stanford University

Observed institution: Stanford University

OpenAlex ID: A5029627872

Inducing Causal Structure for Interpretable Neural Networks

2021 · Geiger, Atticus, Wu, Zhengxuan, et al. · arXiv (Cornell University) · 15

PDF

Causal Distillation for Language Models

2022 · Zhengxuan Wu, Atticus Geiger, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 7

PDF

Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP

2021 · Rozner, Josh, Potts, Christopher, et al. · arXiv (Cornell University) · 7

PDF

Perturbation: A simple and efficient adversarial tracer for representation learning in language models

2026 · Joshua Rozner, Cory Shain · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

BabyLM's First Constructions: Causal probing provides a signal of learning

2025 · Rozner, Joshua, Weissweiler, Leonie, et al. · arXiv (Cornell University)

PDF

Constructions are Revealed in Word Distributions

2025 · Joshua Rozner, Leonie Weissweiler, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

BabyLM’s First Constructions: Causal interventions provide a signal of learning

2025 · Joshua Rozner, Leonie Weissweiler, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Works count: 8

Citation count: 29

H-index: 3

I10-index: 1