institute
active
institute:national-institute-of-informatics-research-and-development-center-for-large-language-modelsNational Institute of Informatics Research and Development Center for Large Language Models
Secondary institutional affiliation of Taura
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.
- Survey of representation engineering methods cited as related work
- The prior Anthropic paper whose findings about emotion features in Claude this paper builds upon and extends
- Prior paper by Shanahan cautioning against anthropomorphic terms for LLMs; cited as ref 1
- Framework describing LLMs as role-play engines, introduced in Shanahan, McDonell, Reynolds 2023.
- Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
- Opening sentence setting the stage for the importance of interpretability.
- Primary test domain for manifold steering, including reasoning and ICL tasks