Skip to content

Jingkai Li

2 papers in the library · publishing 2025

Papers

Sort Most recent Most cited

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

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

arXiv Preprint Archive June 26, 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...

Full text (opens in new tab) Cs.cl Cs.ai Cs.ne Q-bio.nc +20