LoRR augments preference optimization methods like DPO with high-replay training, periodic resets to initial data/policy, and a hybrid objective to improve sample efficiency and reduce primacy bias on math and reasoning tasks.
West-of-n: Synthetic preference generation for improved reward modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sample-efficient LLM Optimization with Reset Replay
LoRR augments preference optimization methods like DPO with high-replay training, periodic resets to initial data/policy, and a hybrid objective to improve sample efficiency and reduce primacy bias on math and reasoning tasks.