Search papers, labs, and topics across Lattice.
3
0
4
Overconfident tokens, often missed by entropy-based methods, carry surprisingly dense corrective signals in on-policy distillation, allowing for near-baseline performance with <10% of tokens.
Reasoning models aren't just verbose, they're actively *harmed* by their own verbosity, but a simple self-distillation trick can compress their outputs by up to 59% while boosting accuracy by up to 16 points.
Overconfident errors in RLVR monopolize probability mass and suppress exploration, but a confidence-aware penalty fixes this and boosts mathematical reasoning performance.
