Conflict Monitoring

The ACC's detection of response conflict, shown to be constitutively emotional rather than purely cognitive

Neighborhood — ranked by edge-count

thinker

Matthew Botvinick
studies
Characterized ACC conflict monitoring and argued conflict functions as an aversive teaching signal

method

Stroop Task
implements
Used to produce response conflict in ACC conflict monitoring studies

concept

Anterior Cingulate Cortex
associated_with
Neural correlate of N380 aha effect in Chinese riddle studies; associated with breaking mental set

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Preference Conflictconcept0.767
Key element for alignment faking: model's pre-existing preferences contradict the new training objective
Gradient conflictconcept0.741
When gradients of different tasks have negative cosine similarity, harming multi-task learning.
intention checkingconcept0.730
Task of checking a model's intentions; found by Lindsey (2026) to peak at ~1/2 depth.
Metacognitive monitoringconcept0.729
Higher-order mechanism that evaluates the reliability of first-order perceptual representations.
Internal conflict in AIconcept0.715
Feature representing dilemmas, inner conflict; used to correct deceptive behavior.
Task balancingconcept0.715
The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
monitorsconcept0.714
Synchronization construct encapsulating shared data and protected access routines.
Correspondence Analysisconcept0.712
Statistical technique providing graphic representation of multidimensional relations among variables using χ² distances; applied here to analyze dependencies among the Fifteen Properties.