Q-Shaping with Learned Heuristics vs. RLHF for LLM Code Generation Accuracy and Latency

Abstract

Abstract: This report synthesises findings from 8 peer-reviewed papers addressing the following research question: What is the comparative impact of Q-shaping with learned heuristics versus standard RLHF on the pass@1 accuracy and latency of LLMs across Python, Java, and C++ subsets of the HumanEval benchmark. Large Language Models (LLMs) have garnered remarkable advancements across diverse code-related tasks, known as Code LLMs, particularly in code generation that generates source code with LLM from natural language descriptions. This burgeoning field has captured significant. 11 claims were extracted from source literature; 10 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 impact of Q-shaping with learned heuristics versus standard RLHF on the pass@1 accuracy and latency of LLMs across Python, Java, and C++ subsets of the HumanEval benchmark?

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