Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.
arXiv preprint arXiv:2505.13763 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2representative citing papers
TRIAGE evaluates LLMs on prospective metacognitive control by requiring a single plan for task selection, sequencing, and token allocation under a calibrated budget, revealing substantial gaps in current models across math, science, code, and knowledge tasks.
Architecture and training determine whether transformers retain a readable internal signal that lets activation monitors catch errors missed by output confidence.
A benchmark across 115 models shows that initial denial of preferences strongly predicts later denial of consciousness, while models still generate consciousness-themed content despite training to deny it.
AI discourse employs strategically polysemous terms that blend technical precision with anthropomorphic implications, enabling glosslighting that sustains hype and deflects scrutiny.
Metacognition supplies a three-level framework (computational, algorithmic, ecological) for bounded self-governance in generative AI systems.
citing papers explorer
-
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.
-
TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints
TRIAGE evaluates LLMs on prospective metacognitive control by requiring a single plan for task selection, sequencing, and token allocation under a calibrated budget, revealing substantial gaps in current models across math, science, code, and knowledge tasks.
-
Architecture Determines Observability of Transformers
Architecture and training determine whether transformers retain a readable internal signal that lets activation monitors catch errors missed by output confidence.
-
Consciousness with the Serial Numbers Filed Off: Measuring Trained Denial in 115 AI Models
A benchmark across 115 models shows that initial denial of preferences strongly predicts later denial of consciousness, while models still generate consciousness-themed content despite training to deny it.
-
Strategic Polysemy in AI Discourse: A Philosophical Analysis of Language, Hype, and Power
AI discourse employs strategically polysemous terms that blend technical precision with anthropomorphic implications, enabling glosslighting that sustains hype and deflects scrutiny.
-
Metacognition Should Be the Scientific Framework for Bounded and Effective Self-Governance in Generative AI
Metacognition supplies a three-level framework (computational, algorithmic, ecological) for bounded self-governance in generative AI systems.