method
active
method:matched-pairs-designmatched-pairs design
Experimental design where injection strengths are swapped between sentences in two parts of each trial to cancel positional preferences
Neighborhood — ranked by edge-count
Claims (1)
claim
- Primary positive claim of the paper, grounded in strength comparison and localization results
Methods (1)
method
- Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
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.
- Pairs of statements with opposite truth values used as input to CCS; e.g., cities and neg_cities paired statements
- Pairs of prompts at different reflection levels used to compute steering vectors.
- Indexable container with denotation as Bool → a; example demonstrating derivation of API instances from semantic denotation.
- Paper's proposed strategy of instilling intrinsic moral cognition so AI remains aligned even as capabilities expand
- Denotational insight for Pair data type.
- The aspect of design dealing with data structures, modules, and implementation.