Input Embedding Similarity Baseline

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

• Input embedding similarity baseline selects semantically related but non-reflective tokens (e.g., Await, ConfigureAwait, Unchecked) that fail to improve accuracyfinding0.853
  Demonstrates the failure mode of surface-level similarity for instruction discovery.
• Steering vector-based instruction discovery outperforms input embedding similarity baseline for reflection-inducing instruction selectionfinding0.779
  Demonstrates that surface-level embedding similarity fails to capture reflective semantics.
• Vector Embedding Representationconcept0.766
  The specific type of representation studied in the paper: function f: X→R^n assigning feature vectors to inputs
• Mutual Embeddingconcept0.764
  A reinforcing interlock between different materials, mentioned alongside Deep Interlock in West Dean construction.
• Activation Similarityconcept0.750
  Model-independent feature comparison based on correlating activation vectors across a fixed diverse dataset
• Certain representation learning algorithms boil down to a simple rule: find an embedding in which similarity equals PMIclaim0.745
  Core theoretical claim about the target of representation learning
• span embedding analysismethod0.740
  Extracting embeddings from instruction and example spans.
• Functional Similarityconcept0.739
  Similarity measured with respect to network behavior/function rather than statistical correlation of activations.