RLMR dynamically adjusts penalties for constraint-violating creative-writing samples during GRPO training and reports gains in IFEval and human preference over fixed-weight baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RLMR: Reinforcement Learning with Mixed Rewards for Creative Writing
RLMR dynamically adjusts penalties for constraint-violating creative-writing samples during GRPO training and reports gains in IFEval and human preference over fixed-weight baselines.