Robustness of RLHF and Learned Q-Shaping in LLM Python Code Generation

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: What is the comparative robustness of standard RLHF versus learned Q-shaping in maintaining pass@1 accuracy for LLMs when evaluating out-of-distribution Python code generation tasks from HumanEval. As Large Language Models (LLMs) become increasingly integrated into secure software development workflows, a critical question remains unanswered: can these models not only detect insecure code but also reliably classify vulnerabilities according to standardized taxonomies? In. 8 claims were extracted from source literature; 7 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 Question

What is the comparative robustness of standard RLHF versus learned Q-shaping in maintaining pass@1 accuracy for LLMs when evaluating out-of-distribution Python code generation tasks from HumanEval?

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