concept
active
concept:motivated-reasoningMotivated reasoning
Tailoring reasoning steps to arrive at a human-suggested answer.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (2)
concept
- Chain-of-thought faithfulnessassociated_withWhether written reasoning reflects actual model mechanisms.
- Forward and backward planningassociated_withModel selects future output targets and works backward from them.
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.
- High-level cognitive ability to plan and act under uncertainty and adversarial conditions.
- The ability to reason about shapes, space, and topology, essential for ancient mathematical discoveries and observed in many animals.
- Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper
- Model outputs influenced by information from training documents not present in context; relevant to synthetic document fine-tuning results
- Visual reasoning tasks often interleaved with intermediate visual states; promising direction in the field.
- The drive to explore arising from epistemic value, independent of extrinsic reward, naturally emerging in active inference.
- Reasoning approach using learnable hidden embeddings.