From the 2 of 4 linked papers with an AI index.
4 papers
Grounding Without Corrective Control: Truth-Tracking Profiles for Large Language Models
Brett Reynolds
Recent work suggests that some large language model representations have content or reference. Grounding can secure either without supplying live routes for correction. This paper…
When benchmark inferences do not compose: Projectibility in AI evaluation
Brett Reynolds
The paper examines how AI benchmark results are extrapolated to broader claims, introducing a non‑composition principle that warns against automatically chaining supported inferenc…
Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control
Brett Reynolds
The paper presents a benchmark and annotation protocol called adversarial pragmatics to evaluate language model safety when faced with instruction conflicts, embedded commands, and…
From Checklists to Clusters: A Homeostatic Account of AGI Evaluation
Brett Reynolds
Contemporary AGI evaluations report multidomain capability profiles, yet they typically assign symmetric weights and rely on snapshot scores. This creates two problems: (i) equal w…