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
Natural Language Processing Journal June 27, 2025 Jingkai Li
Integrated Information Theory (IIT) provides a quantitative framework for explaining consciousness phenomenon, positing that conscious systems comprise elements integrated through causal properties. We apply IIT 3.0 and 4.0 — the latest iterations of this framework — to sequences of Large Language Model (LLM) representations, analyzing data derived from existing Theory of Mind (ToM) test...
DOI: 10.1016/j.nlp.2025.100163 (opens in new tab)
Full text (opens in new tab)
Consciousness
Theory of mind
Integrated information theory
Span representation analysis
+1