Language models show a scale-dependent switch from anticorrelated to correlated reasoning-truthfulness coupling at a family-specific critical parameter count, with architecture and data choices shifting the transition point.
Transactions on Machine Learning Research , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
In agentic AI, safety and fairness are governed by interaction topology rather than model scale or alignment.
Frontier models show positive capability coupling (r=0.72) across SWE-bench and GPQA, with lab-specific emphasis shifts measured by an h-field residual that distinguishes permanent pretraining changes from reversible post-training ones.
citing papers explorer
-
Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
Language models show a scale-dependent switch from anticorrelated to correlated reasoning-truthfulness coupling at a family-specific critical parameter count, with architecture and data choices shifting the transition point.
-
Design and Report Benchmarks for Knowledge Work
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
-
Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment
In agentic AI, safety and fairness are governed by interaction topology rather than model scale or alignment.
-
The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next
Frontier models show positive capability coupling (r=0.72) across SWE-bench and GPQA, with lab-specific emphasis shifts measured by an h-field residual that distinguishes permanent pretraining changes from reversible post-training ones.