artifact

active

artifact:supplementary-code-and-data-at-doi-org-10-1016-j-nlp-2025-100163

Supplementary code and data at doi.org/10.1016/j.nlp.2025.100163

Code, labeled linguistic spans, and augmented responses made publicly available as supplementary material.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Representation Network (RN)
about
Novel construct introduced by this paper: a hypothetical graph embedded in the time series of LLM representations, where each dimension is a node and latent connections are edges.

Concepts (1)

concept

Can 'Consciousness' Be Observed from Large Language Model (LLM) Internal States? Dissecting LLM Representations Obtained from Theory of Mind Test with Integrated Information Theory and Span Representation Analysis
cites
The primary paper being extracted — applies IIT 3.0 and 4.0 to LLM representation sequences derived from ToM test data to investigate whether consciousness phenomena can be observed.