pith. sign in

From faithfulness to correctness: Generative reward models that think critically, 2025

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

RL with Learnable Textual Feedback: A Bilevel Approach

cs.LG · 2026-05-23 · unverdicted · novelty 5.0

Bi-NAC frames RL with textual feedback as a Stackelberg bilevel program and reports that 2B and 6B models trained this way outperform larger GRPO baselines on MATH-500 and GPQA.

citing papers explorer

Showing 1 of 1 citing paper.

  • RL with Learnable Textual Feedback: A Bilevel Approach cs.LG · 2026-05-23 · unverdicted · none · ref 12

    Bi-NAC frames RL with textual feedback as a Stackelberg bilevel program and reports that 2B and 6B models trained this way outperform larger GRPO baselines on MATH-500 and GPQA.