Role-play model of large language models

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

• Large Language Models (LLMs)concept0.809
  Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.
• Language Modelconcept0.807
  Primary test domain for manifold steering, including reasoning and ICL tasks
• Language Modelsconcept0.805
  Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
• Shanahan 2023: Talking about large language modelsconcept0.788
  Prior paper by Shanahan cautioning against anthropomorphic terms for LLMs; cited as ref 1
• Language models are few-shot learners (Brown et al., 2020)concept0.784
  Demonstrated transformers on mathematical understanding and logic; cited to motivate transformer versatility.
• Representation engineering for large-language models: Survey and research challenges (Bartoszcze et al., 2025)concept0.779
  Survey of representation engineering methods cited as related work
• Role Play Framework for Dialogue Agentsframework0.777
  The primary conceptual framework proposed: understanding dialogue agent behaviour as role play of characters
• Andreas 2022: Language models as agent modelsconcept0.775
  Paper hypothesising LLMs model agent beliefs/desires/intentions with preliminary GPT-3 evidence; cited as ref 2