Pairwise preference

Two candidate continuations from one state, with an ordering.

• —`context` and `prompt` define the decision point; `chosen` and `rejected` are the ordered continuations.
• —`critique`, `principle`, and `downstream_evidence` explain why the preference matters.

Samples

• Analogical RL Representation Comparisonview
• Augmentor Policy Handoffsview
• Can a decoding method that measures novelty in a …view
• CRL Importance Samplingview
• How close to optimality are current state-of-the-…view
• Is there a characteristic geometric structure tha…view
• Long-Horizon Offline GCRL Value Errorsview
• RL For Novel LLM Capabilitiesview