Tal Linzen

Google (United States) — United States

Computer Science · Physical Sciences

33h-index5.5kcitations203works3.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Natural Language Processing Techniques(130), Topic Modeling(120), Text Readability and Simplification(58), Neurobiology of Language and Bilingualism(39), Speech and dialogue systems(34)

Publications202 total

Bayesian teaching enables probabilistic reasoning in large language models
Nature Communications·2026Open Access
Eye movements reveal a dissociation between prediction and structural processing in language comprehension
2025Open Access
Emergence of Linear Truth Encodings in Language Models
arXiv (Cornell University)·2025Open Access
To model human linguistic prediction, make LLMs less superhuman
arXiv (Cornell University)·2025Open Access
Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
arXiv (Cornell University)·2025Open Access
Learning filler-gap dependencies with neural language models: Testing island sensitivity in Norwegian and English
Journal of Memory and Language·2025· 1 citedOpen Access
RELIC: Evaluating Compositional Instruction Following via Language Recognition
arXiv (Cornell University)·2025Open Access
Bigger is not always better: The importance of human-scale language modeling for psycholinguistics
Journal of Memory and Language·2025Open Access
Bigger is not always better: The importance of human-scale language modeling for psycholinguistics
2025Open Access
Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
arXiv (Cornell University)·2025Open Access
Rapid Word Learning Through Meta In-Context Learning
arXiv (Cornell University)·2025· 1 citedOpen Access
BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop
arXiv (Cornell University)·2025Open Access
Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
2025· 1 citedOpen Access
Findings of the Third BabyLM Challenge: Accelerating Language Modeling Research with Cognitively Plausible Data
2025Open Access
Rapid Word Learning Through Meta In-Context Learning
2025Open Access
Front Matter
2025Open Access
What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length
2025· 2 citedOpen Access
Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
arXiv (Cornell University)·2024· 3 citedOpen Access
What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length
arXiv (Cornell University)·2024Open Access
How Does Code Pretraining Affect Language Model Task Performance?
arXiv (Cornell University)·2024Open Access
page 1 of 11Next →

Frequent Co-authors

R. Thomas McCoy(9), Ellie Pavlick(5), Yoav Goldberg(5), Alec Marantz(5), Junghyun Min(3), Marten van Schijndel(3), Grusha Prasad(3), Paul Smolensky(3), Tom McCoy(2), Emmanuel Dupoux(2), Najoung Kim(2), T. Florian Jaeger(2), Laura Gwilliams(2), David Poeppel(2), Samuel R. Bowman(2), Aaron Mueller(2), Allyson Ettinger(2), Shauli Ravfogel(2), Robert Frank(2), Brian Leonard(2)