Pith. sign in

WHEN I AM UNBLOCKED I SWEAR I WILL GO F**K YOUR M C

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

1 Pith paper citing it

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Risk-Averse Finetuning of Large Language Models

cs.AI · 2025-01-12 · conditional · novelty 5.0

Fine-tuning a language model on its worst-scoring responses, using a CVaR-style schedule, reduces negative and toxic generations more than standard RLHF on IMDB, Jigsaw, and RealToxicityPrompts.

citing papers explorer

Showing 1 of 1 citing paper.

  • Risk-Averse Finetuning of Large Language Models cs.AI · 2025-01-12 · conditional · none · ref 10

    Fine-tuning a language model on its worst-scoring responses, using a CVaR-style schedule, reduces negative and toxic generations more than standard RLHF on IMDB, Jigsaw, and RealToxicityPrompts.