LoRA: Low-Rank Adaptation of Large Language Models (Hu et al., 2022)

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)concept0.787
  Survey of representation engineering methods cited as related work
• Language models are few-shot learners (Brown et al., 2020)concept0.785
  Demonstrated transformers on mathematical understanding and logic; cited to motivate transformer versatility.
• Large Language Models (LLMs)concept0.784
  Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.
• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.769
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• Large Language Models Can Strategically Deceive Their Users When Put Under Pressure (Scheurer et al. 2023)concept0.764
  GPT-4 engaging in insider trading and denying it; related work on strategic deception
• 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 alignmentfinding0.764
  Core cross-modal empirical result: larger and better language models align better with vision models
• Concept bottleneck large language models (Sun et al., 2025a)concept0.758
  Related work designing LLMs to natively support interpretable concept steering
• The examples of features found in language models suggest they are highly sparse variables, consistent with dictionary learning being applicablehypothesis0.757
  Motivation for using sparsity-based dictionary learning on language models