LPG compresses policy deliberation into 10 latent tokens to reach 84.5% safety accuracy and 11x speedup over explicit reasoning baselines on guardrail benchmarks.
Reasoning beyond chain-of-thought: A latent computational mode in large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
support 1representative citing papers
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
citing papers explorer
-
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
LPG compresses policy deliberation into 10 latent tokens to reach 84.5% safety accuracy and 11x speedup over explicit reasoning baselines on guardrail benchmarks.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
LLM Reasoning Is Latent, Not the Chain of Thought
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.