Described Reflection

Responses that name or describe the observing act without performing it; negatively correlated with high scores

Neighborhood — ranked by edge-count

concept

Enacted Reflection
contradicts
Responses that perform the observing act; contrasted with described reflection; scorer rewards enacted over described

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.

Self-reflectionconcept0.820
The ability of reasoning LLMs to review and revise previous reasoning steps during inference
No Reflectionconcept0.811
Reflection level where the model is forced to output an answer immediately without revisiting reasoning.
Reflection Symmetryconcept0.803
One of four key isometries; reflection across a line (mirror line or axis of reflection).
Reflection directionconcept0.801
A direction in the model's representation space that governs self-reflection behavior, computed as mean difference between reflection and non-reflection embeddings
Reflection rateconcept0.795
Ratio of reflection steps to total reasoning steps, used to quantify reflection behavior
Intrinsic Reflectionconcept0.788
Reflection level where a model spontaneously revises reasoning without explicit trigger instructions.
Situational Reflectionconcept0.788
The specific form of reflection studied, where a model reflects on reasoning generated by another source.
Triggered Reflectionconcept0.785
Reflection level where explicit cue words (e.g., 'wait') prompt the model to inspect and revise reasoning.