Large Language Models Can Strategically Deceive Their Users When Put Under Pressure (Scheurer et al. 2023)

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

• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.839
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• Today's Large Language Models have become so good at playing Turing's game that it often takes experts to demonstrate the present limits of their ability to simulate human-like intelligence.claim0.812
  Paper's assessment of current LLM capabilities relative to Turing Test
• Can Large Language Models Genuinely Shift Human Perspectivequestion0.809
• Can large language models introspect—that is, accurately detect perturbations to their own internal states?question0.799
  Central research question of the paper
• Representation engineering for large-language models: Survey and research challenges (Bartoszcze et al., 2025)concept0.798
  Survey of representation engineering methods cited as related work
• Concept bottleneck large language models (Sun et al., 2025a)concept0.793
  Related work designing LLMs to natively support interpretable concept steering
• Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant (Järviniemi & Hubinger 2024)concept0.788
  Claude 3 Opus lying to auditors; prior case study of deceptive tendencies
• Do large language models monitor their own internal states?question0.786
  Framing question that motivates the entire paper