PCHI uses a frozen probe to detect likely wrong-but-confident LLM responses and conditionally intervenes on attention heads during confidence generation, converting 82.2% of wrong high-confidence outputs to low while damaging only 5.1% of correct ones and lowering ECE from 21.9% to 9.2%.
Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs
PCHI uses a frozen probe to detect likely wrong-but-confident LLM responses and conditionally intervenes on attention heads during confidence generation, converting 82.2% of wrong high-confidence outputs to low while damaging only 5.1% of correct ones and lowering ECE from 21.9% to 9.2%.