IRIS: Interpolative R\'enyi Iterative Self-play for Large Language Model Fine-Tuning

📰 ArXiv cs.AI

arXiv:2604.20933v1 Announce Type: cross Abstract: Self-play fine-tuning enables large language models to improve beyond supervised fine-tuning without additional human annotations by contrasting annotated responses with self-generated ones. Many existing methods rely on a fixed divergence regime. SPIN is closely related to a KL-based regime, SPACE to a Jensen-Shannon-style objective via noise contrastive estimation, and SPIF to $\chi^2$-regularized self-play. Since these divergences exhibit diff

Published 25 Apr 2026

Full Article

Title: IRIS: Interpolative R\'enyi Iterative Self-play for Large Language Model Fine-Tuning

Abstract:
arXiv:2604.20933v1 Announce Type: cross Abstract: Self-play fine-tuning enables large language models to improve beyond supervised fine-tuning without additional human annotations by contrasting annotated responses with self-generated ones. Many existing methods rely on a fixed divergence regime. SPIN is closely related to a KL-based regime, SPACE to a Jensen-Shannon-style objective via noise contrastive estimation, and SPIF to $\chi^2$-regularized self-play. Since these divergences exhibit diff
Read full paper → ← Back to Reads