pith. sign in

Figure 10 | [WMT 2020 Zh-En]:distribution of human preference and reward model scores forReST (BC, I=4, G=1 ) in side by side evaluation with supervised model

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

1 Pith paper citing it

fields

cs.CL 1

years

2023 1

verdicts

UNVERDICTED 1

representative citing papers

Reinforced Self-Training (ReST) for Language Modeling

cs.CL · 2023-08-17 · unverdicted · novelty 6.0

ReST improves LLM translation quality on benchmarks via offline RL on self-generated data, achieving gains in a compute-efficient way compared to typical RLHF.

citing papers explorer

Showing 1 of 1 citing paper.

  • Reinforced Self-Training (ReST) for Language Modeling cs.CL · 2023-08-17 · unverdicted · none · ref 31

    ReST improves LLM translation quality on benchmarks via offline RL on self-generated data, achieving gains in a compute-efficient way compared to typical RLHF.