concept

active

concept:gwt-4-state-dependent-attention-enabling-sequential-querying-of-modules-for-complex-tasks

GWT-4: State-dependent attention enabling sequential querying of modules for complex tasks

Indicator: state-dependent attention and sequential module recruitment for System 2 thought.

Neighborhood — ranked by edge-count

Papers (1)

paper

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
introduces

Frameworks (1)

framework

Global workspace theory
associated_with
Theory of consciousness involving a global workspace for information.

Concepts (2)

concept

GWT-4: State-dependent attention, giving rise to the capacity to use the workspace to query modules in succession to perform complex tasks
related_to
Fourth GWT indicator; links global workspace to working memory and complex task performance; entails RPT-1
State-dependent attention
associated_with
Attention where selection depends on the current state of the system, enabling top-down control.

Related by similarity (8)

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.

GWT-1: Multiple specialized systems capable of operating in parallel (modules)concept0.811
First of four GWT indicators; claimed necessary for consciousness alongside GWT-2 through GWT-4
GWT-2: Limited capacity workspace, entailing a bottleneck and a selective attention mechanismconcept0.805
Indicator: workspace bottleneck with selective attention.
GWT-1: Multiple specialised systems capable of operating in parallel (modules)concept0.799
Indicator from GWT: existence of specialized parallel modules.
GWT-2: Limited capacity workspace, entailing a bottleneck in information flow and selective attention mechanismconcept0.781
Second GWT indicator; the bottleneck and attention mechanism constituting the workspace
GWT-3: Global broadcast: availability of information in the workspace to all modulesconcept0.759
Indicator: global broadcast to all modules.
Perceiver architecture is some way from being a full implementation of GWT.claim0.729
Case study conclusion.
Directing response attention to complement syntax and/or mental state verbs (MSV) yields no significant alterations in IIT estimates compared to entire stimulus analysis.finding0.729
Suggests LLMs do not represent complement/MSV linguistic features in the same way as they are crucial for human ToM development.
sequential reasoning tasksconcept0.727
Language model reasoning tasks with sequential geometry used in experiments.