method
active
method:star-self-taught-reasonerSTaR (Self-Taught Reasoner)
A method for improving reasoning by self-training on rationales.
Neighborhood — ranked by edge-count
Artifacts (1)
artifact
- Simulators (LessWrong post)mentionsThe paper being extracted.
Related by similarity (2)
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.
- Fine-tuning on Claude-generated self-correction examples with loss masking to induce ESR-like behavior
- Raileanu et al. 2018 - Modeling Others Using Oneself in Multi-Agent Reinforcement Learningconcept0.651Reference for Self-Other Modeling (SOM) framework, a related but less scalable approach to SOO