ConceptCounterfactual Credit Reweighting
Counterfactual Credit Reweighting
A fine-grained credit assignment method for supervised fine-tuning of agents that weights each reasoning and action step by its counterfactual contribution to the final answer, amplifying useful steps and suppressing ineffective or misleading ones.
Timeline (last 90 days)
Nov 3
The study proposes a counterfactual credit reweighting method that weights each reasoning and action step according to its counterfactual contribution to the final answer, in order to handle noisy teacher trajectories.
Unverified50%