·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Vision Hopfield Memory Networks0m◆Stable Deep Reinforcement Learning via Isotropic Gaussian Representations0m◆SentinelBench: A Benchmark for Long-Running Monitoring Agents0m◆An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)0m◆Synthetic Contrastive Reasoning for Multi-Table Q&A0m◆Residual Modeling for High-Fidelity Learned Compression of Scientific Data0m◆Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution0m◆A Motivational Architecture for Conversational AGI0m◆Assessing the Carbon Emissions and Energy Consumption of U.S. Hyperscale Data Centers0m◆Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models0m◆Zero knowledge verification for frontier AI training is possible0m◆Brick-Composer: Using MLLMs for Assembly with Diverse Bricks0m◆Insurance of Agentic AI0m◆Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety0m◆PSEBench: A Controllable and Verifiable Benchmark for Evaluating LLMs in Patient Safety Event Triage0m◆Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces0m◆Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation0m◆SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization0m◆When Should We Protect AI? A Precautionary Framework for Consciousness Uncertainty0m◆Individual Gain, Collective Loss: Metacognitive Adaptation in AI-Assisted Creativity0m◆Vision Hopfield Memory Networks0m◆Stable Deep Reinforcement Learning via Isotropic Gaussian Representations0m◆SentinelBench: A Benchmark for Long-Running Monitoring Agents0m◆An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)0m◆Synthetic Contrastive Reasoning for Multi-Table Q&A0m◆Residual Modeling for High-Fidelity Learned Compression of Scientific Data0m◆Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution0m◆A Motivational Architecture for Conversational AGI0m◆Assessing the Carbon Emissions and Energy Consumption of U.S. Hyperscale Data Centers0m◆Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models0m◆Zero knowledge verification for frontier AI training is possible0m◆Brick-Composer: Using MLLMs for Assembly with Diverse Bricks0m◆Insurance of Agentic AI0m◆Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety0m◆PSEBench: A Controllable and Verifiable Benchmark for Evaluating LLMs in Patient Safety Event Triage0m◆Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces0m◆Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation0m◆SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization0m◆When Should We Protect AI? A Precautionary Framework for Consciousness Uncertainty0m◆Individual Gain, Collective Loss: Metacognitive Adaptation in AI-Assisted Creativity0m◆
News/Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
arxiv
PublishedMay 18, 2026 at 4:00 AM
—neutral

Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.15440v1 Announce Type: new Abstract: Surprisal theory posits that the processing difficulty of a word is determined by its predictability in context, offering a potential link between human sentence processing and next-word predictions from language models. While language model (LM) surpr

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Mentioned models
01
  • 01
    Recurrent Neural Network Grammars (RNNGs)
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#language-models#sentence-processing#syntactic-ambiguity#reading-times

No replies yet. Be first.

Mentioned models
01
  • 01
    Recurrent Neural Network Grammars (RNNGs)
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#language-models#sentence-processing#syntactic-ambiguity#reading-times

Related coverage

More from ARXIV
arxivVision Hopfield Memory Networks0marxivStable Deep Reinforcement Learning via Isotropic Gaussian Representations0marxivA Motivational Architecture for Conversational AGI0marxivAssessing the Carbon Emissions and Energy Consumption of U.S. Hyperscale Data Centers0m
The Bubble Brief
WEEKLY

Read language-models insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews