LLMs detect CoT reasoning errors in hidden states with 0.95 AUROC but cannot use this awareness to correct them via steering, patching, or self-correction, indicating the signal is diagnostic not causal.
The internal state of an
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.
citing papers explorer
-
Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
LLMs detect CoT reasoning errors in hidden states with 0.95 AUROC but cannot use this awareness to correct them via steering, patching, or self-correction, indicating the signal is diagnostic not causal.
-
Common-agency Games for Multi-Objective Test-Time Alignment
CAGE uses common-agency games and an EPEC algorithm to compute equilibrium policies that balance multiple conflicting objectives for test-time LLM alignment.