claim
active
claim:aos-might-be-too-expressive-so-explanations-may-reflect-the-ao-s-understanding-rather-than-the-target-llm-s

AOs might be too expressive, so explanations may reflect the AO's understanding rather than the target LLM's

Limitation; confabulation risk.

Neighborhood — ranked by edge-count

Concepts (1)

concept

Methods (1)

method
  • Simple linear classifiers trained on model activations used as the probing technique within the introduced method.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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