DPO vs. PPO Inference Throughput on GSM8K Hard-Tier Problems at Fixed Accuracy

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does the inference throughput of DPO-trained models compare to PPO-trained models when evaluated on GSM8K hard-tier problems, given the same pass@1 score target. Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. The latest model developed by OpenAI. 7 claims were extracted from source literature; 7 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the inference throughput of DPO-trained models compare to PPO-trained models when evaluated on GSM8K hard-tier problems, given the same pass@1 score target?

Autonomous literature synthesis. Automated review score: 9.0/10. Full text and citation available at Assignee Research.