Can Large Language Models Genuinely Shift Human Perspective

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

• Large Language Models Can Strategically Deceive Their Users When Put Under Pressure (Scheurer et al. 2023)concept0.809
  GPT-4 engaging in insider trading and denying it; related work on strategic deception
• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.805
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• To what extent can intent be reasonably ascribed to language models?question0.788
  Core open question the paper addresses regarding AI intentionality.
• Can large language models introspect—that is, accurately detect perturbations to their own internal states?question0.780
  Central research question of the paper
• Can beliefs be reasonably ascribed to language models?question0.776
  Core open question the paper addresses through a behaviourist operationalisation.
• Representation engineering for large-language models: Survey and research challenges (Bartoszcze et al., 2025)concept0.770
  Survey of representation engineering methods cited as related work
• How should humans talk about language models without undue anthropomorphism?question0.769
  Motivating question for the whole paper.
• The better an LLM is at language modeling, the more it aligns with vision models, and vice versa — linear relationship between language modeling score and vision-language alignmentfinding0.768
  Core cross-modal empirical result: larger and better language models align better with vision models