pith. sign in

Sub-task decomposition enables learning in sequence to sequence tasks

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

PARM: Pipeline-Adapted Reward Model

cs.AI · 2026-04-20 · unverdicted · novelty 6.0

PARM adapts reward models to multi-stage LLM pipelines via pipeline data and direct preference optimization, improving execution rate and solving accuracy on optimization benchmarks and showing transfer to GSM8K.

citing papers explorer

Showing 1 of 1 citing paper.

  • PARM: Pipeline-Adapted Reward Model cs.AI · 2026-04-20 · unverdicted · none · ref 16

    PARM adapts reward models to multi-stage LLM pipelines via pipeline data and direct preference optimization, improving execution rate and solving accuracy on optimization benchmarks and showing transfer to GSM8K.