concept
active
concept:reasoning-modelsReasoning Models
Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
Neighborhood — ranked by edge-count
Papers (2)
paper
Concepts (2)
concept
- Reasoning modelsame_asModels like R1 that produce chain-of-thought and backtrack; claimed qualitatively different from non-reasoning LMs.
- CoT monitoringassociated_withMonitoring CoT to detect misaligned intentions; paper tests its reliability.
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.
- Probability of data under the model, penalizing complexity and rewarding accuracy.
- Future direction.
- Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
- A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
- Primary test domain for manifold steering, including reasoning and ICL tasks
- Success in cognitive science motivates the approach.
- Tailoring reasoning steps to arrive at a human-suggested answer.
- Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.