Skip to content

Author

Rongyi Lin

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists. A judge checks each criterion of a rubric, and the verdicts are aggregated into a reward, most often by a weighted sum. We show that this additive aggregation is the weak point. Under a sum, criteria compensate for one anot...

Mao-Qi Liu, Jun-Wei He, Bo-Wen Zhang et al. · 0 citations
Jul 2026

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

CoRT is proposed, a token-level credit weighting method for rubric-conditioned GRPO that uses counterfactual replay to rescore the same sampled response under the original rubric-conditioned prompt and a matched criteria-free prompt, and suggests that policy-internal counterfactual likelihood contrasts provide an effec...

Bo-Wen Zhang, Jun-Wei He, Wen Wang et al. · 5 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.