works on
counterfactual replay 1language models 1reinforcement learning 1rubric-based evaluation 1token-level credit 1

From the 1 of 7 linked papers with an AI index.

most citedStructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Bo-Wen Zhang, Junwei He, Wen Wang +5

The paper introduces CoRT, a method that uses counterfactual replay to assign token-level credit in rubric-guided reinforcement learning for language models, improving credit alloc…