James A. Michaelov

32 papers A* 1B 6Journal 21Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
How Open Must Language Models be to Enable Reliable Scientific Inference?
CoRR
James A. Michaelov, Catherine Arnett, Tyler A. Chang, Pamela D. Rivière, Samuel M. Taylor, Cameron R. Jones, Sean Trott, Roger P. Levy, Benjamin K. Bergen, Micah Altman
2026 J jnl
Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs.
CoRR
Sean Trott, Samuel M. Taylor, Cameron R. Jones, James A. Michaelov, Pamela D. Rivière
2026 J jnl
N-gram-like Language Models Predict Reading Time Best.
CoRR
James A. Michaelov, Roger P. Levy
2025 J jnl
Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction.
CoRR
James A. Michaelov, Catherine Arnett
2025 J jnl
Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale.
CoRR
James A. Michaelov, Roger P. Levy, Benjamin K. Bergen
2025 — conf
Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events.
ACL (Findings)
James A. Michaelov, Reeka Estacio, Zhien Zhang, Ben Bergen
2025 J jnl
Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events.
CoRR
James A. Michaelov, Reeka Estacio, Zhien Zhang, Benjamin K. Bergen
2025 — conf
On the Acquisition of Shared Grammatical Representations in Bilingual Language Models.
ACL (1)
Catherine Arnett, Tyler A. Chang, James A. Michaelov, Ben Bergen
2025 J jnl
On the Acquisition of Shared Grammatical Representations in Bilingual Language Models.
CoRR
Catherine Arnett, Tyler A. Chang, James A. Michaelov, Benjamin K. Bergen
2024 J jnl
Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics.
CoRR
James A. Michaelov, Catherine Arnett, Benjamin K. Bergen
2023 B conf
Can Peanuts Fall in Love with Distributional Semantics?
CogSci
James A. Michaelov, Seana Coulson, Benjamin Bergen
2023 J jnl
Can Peanuts Fall in Love with Distributional Semantics?
CoRR
James A. Michaelov, Seana Coulson, Benjamin K. Bergen
2023 J jnl
Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Models.
CoRR
Catherine Arnett, Tyler A. Chang, James A. Michaelov, Benjamin K. Bergen
2023 J jnl
Do Large Language Models Know What Humans Know?
Cogn. Sci.
Sean Trott, Cameron R. Jones, Tyler A. Chang, James A. Michaelov, Benjamin K. Bergen
2023 — conf
Emergent Inabilities? Inverse Scaling Over the Course of Pretraining.
EMNLP (Findings)
James A. Michaelov, Ben Bergen
2023 J jnl
Emergent inabilities? Inverse scaling over the course of pretraining.
CoRR
James A. Michaelov, Benjamin K. Bergen
2023 — conf
Rarely a problem? Language models exhibit inverse scaling in their predictions following few-type quantifiers.
ACL (Findings)
James A. Michaelov, Benjamin K. Bergen
2023 J jnl
So Cloze Yet So Far: N400 Amplitude Is Better Predicted by Distributional Information Than Human Predictability Judgements.
IEEE Trans. Cogn. Dev. Syst.
James A. Michaelov, Seana Coulson, Benjamin K. Bergen
2023 A* conf
Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models.
EMNLP
James A. Michaelov, Catherine Arnett, Tyler A. Chang, Ben Bergen
2023 J jnl
Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models.
CoRR
James A. Michaelov, Catherine Arnett, Tyler A. Chang, Benjamin K. Bergen
2022 J jnl
'Rarely' a problem? Language models exhibit inverse scaling in their predictions following 'few'-type quantifiers.
CoRR
James A. Michaelov, Benjamin K. Bergen
2022 B conf
Collateral facilitation in humans and language models.
CoNLL
James A. Michaelov, Benjamin K. Bergen
2022 J jnl
Collateral facilitation in humans and language models.
CoRR
James A. Michaelov, Benjamin K. Bergen
2022 B conf
Distrubutional Semantics Still Can't Account for Affordances.
CogSci
Cameron R. Jones, Tyler A. Chang, Seana Coulson, James A. Michaelov, Sean Trott, Benjamin Bergen
2022 B conf
Do Language Models Make Human-like Predictions about the Coreferents of Italian Anaphoric Zero Pronouns?
COLING
James A. Michaelov, Benjamin K. Bergen
2022 J jnl
Do Large Language Models know what humans know?
CoRR
Sean Trott, Cameron R. Jones, Tyler A. Chang, James A. Michaelov, Benjamin K. Bergen
2022 J jnl
Do language models make human-like predictions about the coreferents of Italian anaphoric zero pronouns?
CoRR
James A. Michaelov, Benjamin K. Bergen
2021 B conf
Different kinds of cognitive plausibility: why are transformers better than RNNs at predicting N400 amplitude?
CogSci
James A. Michaelov, Megan D. Bardolph, Seana Coulson, Benjamin Bergen
2021 J jnl
Different kinds of cognitive plausibility: why are transformers better than RNNs at predicting N400 amplitude?
CoRR
James A. Michaelov, Megan D. Bardolph, Seana Coulson, Benjamin K. Bergen
2021 J jnl
So Cloze yet so Far: N400 Amplitude is Better Predicted by Distributional Information than Human Predictability Judgements.
CoRR
James A. Michaelov, Seana Coulson, Benjamin K. Bergen
2020 B conf
How well does surprisal explain N400 amplitude under different experimental conditions?
CoNLL
James A. Michaelov, Benjamin K. Bergen
2020 J jnl
How well does surprisal explain N400 amplitude under different experimental conditions?
CoRR
James A. Michaelov, Benjamin K. Bergen