concept
active
concept:intrinsic-reflectionIntrinsic Reflection
Reflection level where a model spontaneously revises reasoning without explicit trigger instructions.
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- The paper's proposed categorization of reflection into No Reflection, Intrinsic Reflection, and Triggered Reflection.
Concepts (2)
concept
- No ReflectionextendsReflection level where the model is forced to output an answer immediately without revisiting reasoning.
- Triggered ReflectionextendsReflection level where explicit cue words (e.g., 'wait') prompt the model to inspect and revise reasoning.
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.
- The ability of reasoning LLMs to review and revise previous reasoning steps during inference
- The specific form of reflection studied, where a model reflects on reasoning generated by another source.
- Responses that name or describe the observing act without performing it; negatively correlated with high scores
- The capacity to determine behaviour based on reflective normative/evaluative judgment.
- Responses that perform the observing act; contrasted with described reflection; scorer rewards enacted over described
- One of four key isometries; reflection across a line (mirror line or axis of reflection).
- A direction in the model's representation space that governs self-reflection behavior, computed as mean difference between reflection and non-reflection embeddings
- Ratio of reflection steps to total reasoning steps, used to quantify reflection behavior