pith. sign in

We have also tried different sampling batch size and gradient update batch size to vary the maximum number of off-policy update

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

The Unlearnability Phenomenon in RLVR for Language Models

cs.LG · 2026-05-16 · unverdicted · novelty 7.0

RLVR training for language models exhibits an unlearnability phenomenon where certain hard examples stay unlearnable due to low gradient similarity and ungeneralizable reasoning patterns.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Unlearnability Phenomenon in RLVR for Language Models cs.LG · 2026-05-16 · unverdicted · none · ref 3

    RLVR training for language models exhibits an unlearnability phenomenon where certain hard examples stay unlearnable due to low gradient similarity and ungeneralizable reasoning patterns.