DART filters and rewrites expert reasoning demonstrations with the student model's own rollouts, then fine-tunes on those outcome-consistent adapted trajectories.
11 Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, and Radha Poovendran
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration
DART filters and rewrites expert reasoning demonstrations with the student model's own rollouts, then fine-tunes on those outcome-consistent adapted trajectories.