Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following
CALIF is a lightweight method that augments verifier rewards with a calibrated likelihood-based bonus to preserve response quality and outperforms corresponding base policies in 40 of 45 model-metric comparisons across three rubric-based instruction-following benchmarks.
Sangyeon Yoon, Wooseok Seo, Hamish Ivison et al.
· 0 citations