Multimodal Input Integration in DeepSeek R1 and Codestral for Vulnerability Repair

Abstract

Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How does the integration of multimodal inputs (e.g., AST + control flow graphs) affect the vulnerability repair capabilities of DeepSeek R1 versus Codestral, measured by accuracy and throughput on. With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 4.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the integration of multimodal inputs (e.g., AST + control flow graphs) affect the vulnerability repair capabilities of DeepSeek R1 versus Codestral, measured by accuracy and throughput on the Big-Vul dataset?

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