LM Intention

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• LM Beliefconcept0.846
  Contentious concept operationalised behaviourally as consistent outputs of P or similar content when directly asked about P.
• LLM Meta-Cognitionconcept0.792
  The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
• LLM Self-Correctionconcept0.779
  Related capability where LLMs correct their own outputs, studied via linear representations.
• LLM psychosisconcept0.773
  Tendency for models to get lost in roleplay or doom spirals, mitigated by expanded awareness.
• LLM Personalizationconcept0.770
  Related field aiming to tailor assistant behavior to individual users, contrasted with character training's broader persona approach
• Logical Coherence of LM Beliefsconcept0.769
  The extent to which an LM's beliefs respect logical entailment: if it believes A and A→B, it should also believe B.
• LLM-Judge Data Attributionmethod0.764
  Alternative data attribution approach using an LLM as a judge; compared against the probe-based method.
• LLM-as-a-Judgeframework0.760
  Evaluation framework using an LLM (GPT-4.1-mini) to score trait expression and coherency