Showing 1–20 of 63 results
/ Date/ Name
May 1, 2020Predicting Declension Class from Form and MeaningJun 4, 2021Modeling the Unigram DistributionSep 8, 2021A Bayesian Framework for Information-Theoretic ProbingApr 25, 2021What About the Precedent: An Information-Theoretic Analysis of Common LawNov 28, 2023Quantifying the redundancy between prosody and textNov 27, 2023An Exploration of Left-Corner TransformationsApr 19, 2022Probing for the Usage of Grammatical NumberApr 9, 2024On the Effect of (Near) Duplicate Subwords in Language ModellingDec 19, 2024Tokenisation is NP-CompleteNov 11, 2022The Architectural Bottleneck PrincipleJul 7, 2023Testing the Predictions of Surprisal Theory in 11 LanguagesFeb 17, 2026Operationalising the Superficial Alignment Hypothesis via Task ComplexityDec 20, 2022A Measure-Theoretic Characterization of Tight Language ModelsApr 7, 2020Information-Theoretic Probing for Linguistic StructureMay 4, 2020A Tale of a Probe and a ParserJun 6, 2024Causal Estimation of Memorisation ProfilesJun 3, 2025Causal Estimation of Tokenisation BiasOct 23, 2024Towards a Similarity-adjusted Surprisal TheoryDec 8, 2025Do Generalisation Results Generalise?Sep 28, 2021On Homophony and Rényi Entropy