pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2026 1 2025 1

representative citing papers

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward

cs.LG · 2026-05-11 · unverdicted · novelty 6.0

VIGOR assigns higher rewards to LLM completions that produce smaller l2 norms of teacher-forced negative log-likelihood gradients, with sqrt(T) length correction and group ranking, yielding +3.31% math and +1.91% code gains over RLIF on Qwen2.5-7B.

citing papers explorer

Showing 2 of 2 citing papers.