model
open-checkpoint models
modelactiveprovisional
open-checkpoint-models-626b1a92·1 events·first seen 16d agoAliases: open-checkpoint models
Co-occurring entities
More like this (12)
closed-weight modelsstable-worldmodelContinuous-Time Consistency Modelsalignment auditingopen-weight modelsSIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Modelcopy-on-writeShuffle Modelleave-one-out baselineDynamic-Probabilistic Consistency Gapfoundation modelsSelection Without Signal, Recovery Through Expression: A Measurement Study of Post-Hoc Falsification Operators for Frozen Small Code Models
Recent events (1)
Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions
This paper investigates whether language models can learn the semantics of rare English constructions (e.g., 'let alone', 'much less'), constructing a novel dataset to test form-meaning pairing understanding. Testing models across parameter counts, architectures, and pretraining dataset sizes, the authors find that modestly sized open-source models can grasp Paired-Focus construction semantics, while models trained on human-scale data fail. Training dynamics analysis reveals that semantic understanding of these constructions emerges later than syntactic knowledge and correlates with gains in world knowledge more broadly.