Direct Preference Optimization and RLHF Throughput in Adversarial Code Generation on HEIGER

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How does the throughput of DPO compare to RLHF when evaluating LLMs on the HEIGER benchmark for adversarial code generation tasks with varying model sizes. Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article provides a concise mathematical reference for. 17 claims were extracted from source literature; 15 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the throughput of DPO compare to RLHF when evaluating LLMs on the HEIGER benchmark for adversarial code generation tasks with varying model sizes?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.