Concept bottleneck large language models (Sun et al., 2025a)

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

• Representation engineering for large-language models: Survey and research challenges (Bartoszcze et al., 2025)concept0.806
  Survey of representation engineering methods cited as related work
• Large Language Models Can Strategically Deceive Their Users When Put Under Pressure (Scheurer et al. 2023)concept0.793
  GPT-4 engaging in insider trading and denying it; related work on strategic deception
• Shanahan 2023: Talking about large language modelsconcept0.789
  Prior paper by Shanahan cautioning against anthropomorphic terms for LLMs; cited as ref 1
• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.781
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• Large Language Models (LLMs)concept0.781
  Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.
• Language models are some of the most remarkable computer programs in existence.quote0.779
  Opening sentence setting the stage for the importance of interpretability.
• Language models are few-shot learners (Brown et al., 2020)concept0.776
  Demonstrated transformers on mathematical understanding and logic; cited to motivate transformer versatility.
• Emotion Concepts and their Function in a Large Language Modelconcept0.769
  The prior Anthropic paper whose findings about emotion features in Claude this paper builds upon and extends