finding
active
finding:lexical-contribution-amplified-near-positional-index-but-suppressed-near-reflexive-indexLexical contribution amplified near positional index but suppressed near reflexive index
Interaction patterns in Figure 3.
Source paper
extracted_from(2025) · Yoav Gur-Arieh · Mor Geva · Atticus Geiger
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central thesis.
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.
- Lexical and reflexive mechanisms provide sharper signals refining the diffuse positional signalclaim0.784Takeaway.
- Learned parameters.
- Ablation depends on t_entity.
- §D.3.
- When lexical/reflexive targets absent from original, model falls back to noisy positional mechanismfinding0.756Fig. 28–29.
- Lexical signal can be derived locally from query token while reflexive must be retrieved from entity tokenshypothesis0.736Tested with knockout.
- Comparative prediction motivating future work contrasting different approaches to LLM self-knowledge