DIVE: Diversified Iterative Self-Improvement
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:UWXCVOLRrecord.jsonopen to challenge →
read the original 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. Code is available at https://github.com/qinyiwei/DIVE.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Anchorless Diversification for Parallel LLM Ideation
Semantic direction stratification yields the best diversity-quality-compute frontier for parallel LLM ideation across creative tasks.
-
Unlocking LLM Creativity in Science through Analogical Reasoning
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.