pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CL 1

years

2020 1

verdicts

CONDITIONAL 1

representative citing papers

Learning to summarize from human feedback

cs.CL · 2020-09-02 · conditional · novelty 7.0

Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning to summarize from human feedback cs.CL · 2020-09-02 · conditional · none · ref 48

    Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.