Conditional Equivalence of DPO and RLHF in Adversarial Code Generation Throughput

Abstract

Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: What is the throughput impact of using DPO versus RLHF for alignment when evaluating LLMs on the HEIGER benchmark for adversarial code generation tasks. Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather than universal, depending on an implicit. 12 claims were extracted from source literature; 5 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 6.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

What is the throughput impact of using DPO versus RLHF for alignment when evaluating LLMs on the HEIGER benchmark for adversarial code generation tasks?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance