Anthropomorphism of LMs

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

• Anthropomorphism of AIconcept0.818
  Tendency of the model to recruit human-like mental concepts when representing its assistant persona.
• A formal behaviourist framework can describe LM behaviour precisely in intuitive language without undue anthropomorphism.claim0.765
  Central thesis of the paper: behaviourism provides adequate formal grounding for LM character attribution.
• Linear mixed-effects models (LMMs)method0.740
  Primary statistical model with random intercept by conversation, REML estimation, for pooled conversation-turn observations
• Anthropocentrismconcept0.731
  The belief that human intelligence is the norm, against which other intelligences are measured.
• The charge of ‘anthropomorphism’ is a pre-scientific world view that assumes human uniqueness.claim0.728
  Defense against the common critique of attributing agency to non-human systems.
• Understanding how LMs learn linguistic behaviours may offer insights into fundamental properties of languagehypothesis0.727
  Forward-looking hypothesis linking LM mechanism analysis to linguistic theory
• Undue anthropomorphism is surely detrimental to the public conversation on AIclaim0.722
  Normative motivation for the paper's conceptual contribution
• Linear World Models in LLMsframework0.721
  Prior work framework studying whether LLMs encode world models as linear structures in their representations