pith. sign in

To maintain consistency in data volume with the baselines as discussed in §5.3, we sampled the same 8K data points for training

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Sample-efficient LLM Optimization with Reset Replay

cs.LG · 2025-08-08 · unverdicted · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Sample-efficient LLM Optimization with Reset Replay cs.LG · 2025-08-08 · unverdicted · none · ref 22

    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.