Can language models genuinely introspect on internal states or only confabulate?

{
  "doc": "lindsey-introspective-awareness-2026.md",
  "author": null,
  "context": "Central research question animating the paper: distinguishing genuine introspection from illusion through causal manipulation of activations.",
  "category": "ai",
  "enrichment": {
    "is_stale": true
  },
  "norm_label": "Can language models genuinely introspect on internal states or only confabulate?",
  "source_url": null,
  "graphify_id": "q_genuine_introspection",
  "source_file": "lindsey-introspective-awareness-2026.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/lindsey-introspective-awareness-2026/graph.json",
  "extracted_type": "question",
  "source_location": "Abstract, §1",
  "graphify_file_type": "question"
}