Andreas 2022: Language models as agent models

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

• Language Modelsconcept0.808
  Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
• Language Modelconcept0.800
  Primary test domain for manifold steering, including reasoning and ICL tasks
• Agent-based modellingmethod0.799
  Computational method used to simulate zombie ant behavior.
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.782
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach
• Autoregressive Language Modelingconcept0.779
  Training objective interpretable as optimizing a diverse set of tasks; thus subject to multitask scaling convergence pressures
• Agent-based computational modelmethod0.776
  The computational approach used to simulate morphogenesis with cells as agents on a 2D grid; allows quantitative testing of stress-sharing hypothesis.
• Role-play model of large language modelsframework0.775
  Framework describing LLMs as role-play engines, introduced in Shanahan, McDonell, Reynolds 2023.
• Perez et al. 2022: Discovering language model behaviors with model-written evaluationsconcept0.771
  Study showing RLHF can exacerbate self-preservation tendencies in LLMs; key empirical support for a paper claim