concept
active
concept:hallucination-in-llms

Hallucination in LLMs

Problem cited as a shortcoming of current LLMs; PRH predicts hallucinations should decrease with scale

Neighborhood — ranked by edge-count

Claims (1)

claim

Hypotheses (1)

hypothesis

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.

  • LLM psychosisconcept0.816
    Tendency for models to get lost in roleplay or doom spirals, mitigated by expanded awareness.
  • Directions in activation space associated with contrastive emotive concept pairs studied in this paper as targets for introspection
  • Prior work documenting abrupt capability changes under scale; UCCT provides a measurable predictor for when they occur
  • LLM Meta-Cognitionconcept0.771
    The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
  • Sycophancy in LLMsconcept0.768
    Tendency of LLMs to please the user; identified as a danger in spiritual contexts.
  • hallucinationconcept0.764
    Model tendency to generate incorrect intermediate reasoning steps that mislead answer inference, particularly in 1B-models.
  • Lindsey 2026 paper finding that models can articulate content of injected activation patterns; supports claim about self-knowledge representations
  • The finding that interpretable concepts including character traits are encoded as linear directions in transformer residual streams