AI Paper Atlas

Research map / Large language models / Alignment and preferences

Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO

Shokichi Takakura, Akifumi Wachi, Rei Higuchi, Kohei Miyaguchi, Taiji Suzuki

ICML 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
meta-train with non-linear GRPO (IAMA) instead of standard GRPO on the averaged rewardMistral 7B Instruct · Length reward on UltraFeedback (target lengths 50 and 150)response length distribution of base modelImproved
increase N in BoN (or lower tau in soft BoN) in the IAMA objective (ablation)Mistral 7B Instruct with non-linear GRPO · Length reward on UltraFeedbackpolarization of response lengthsImproved
apply BoN (N=4) sampling at inference on IAMA-trained modelAlpaca 7B with non-linear GRPO · hh-rlhf helpfulness vs harmlessnessPareto front of golden rewardsImproved
use IAMA instead of standard alignment when no BoN sampling is applied at inferenceAlpaca 7B · hh-rlhf helpfulness vs harmlessnessgolden rewards without BoNNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy