How does 4-bit quantization influence the alignment of LLaMA 3.2 and Mistral with human preferences in code re

Abstract

Abstract: Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair – in which the model debugs and repairs its own code – has recently become a popular way to boost performance in these settings. However, despite its increasing popularity, existing studies of self-repair have been limited in scope; in many settings, its efficacy thus remains poorly understood. In this paper, we analyze Code Llama, GPT-3.5 and GPT-4's ability to perform self-repair on problems taken from HumanEval and APPS. We find that when the cost of carrying o

Research Question

How does 4-bit quantization influence the alignment of LLaMA 3.2 and Mistral with human preferences in code repair tasks as evaluated by the TruthfulQA 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