concept
active
concept:multi-attempt-rate-metricMulti-Attempt Rate (metric)
Secondary metric: percentage of responses containing multiple attempts, separating surface from actual self-correction
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Endogenous Steering ResistanceimplementsThe central phenomenon introduced by this paper: inference-time recovery from irrelevant activation steering in LLMs
Conceptual bridges
2-hop · via this concept's ideasWhere ideas in this concept connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.
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.
- A response containing multiple distinct attempts to answer the prompt, used as primary metric for ESR
- Quantitative characterization of ESR operating regime in boost level sweep
- Primary metric: percentage of responses containing multiple attempts that successfully improve on the first attempt
- Framework for optimizing multiple objectives simultaneously, used in MTL.
- Key finding pattern where fine-tuning increases attempt rate but not correction success rate
- Philosophical framework asserting same function can be implemented by very different systems; key to arguing sentience is substrate-independent.
- Using language model log probabilities of answer choices (A)/(B) to produce preference labels.