DIVE: Diversified Iterative Self-Improvement

ACL ARR 2025 May Submission5537 Authors

Abstract: Recent advances in large language models (LLMs) have demonstrated the effectiveness of Iterative Self-Improvement (ISI) techniques. However, continuous training on self-generated data leads to reduced output diversity, a limitation particularly critical in reasoning tasks where diverse solution paths are essential. We present DIVE (Diversified Iterative Self-Improvement), a novel framework that addresses this challenge through two key components: Sample Pool Expansion for broader solution exploration, and Data Selection for balancing diversity and quality in preference pairs. Experiments on MATH and GSM8k datasets show that DIVE achieves a 10\% to 45\% relative increase in output diversity metrics while maintaining performance quality compared to vanilla ISI. Our ablation studies confirm both components' significance in achieving these improvements.

Paper Type: Long

Research Area: Machine Learning for NLP

Research Area Keywords: self-supervised learning, contrastive learning, generative models

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5537