Alignment Techniques and Reasoning Performance in Vision-Language Models on Mixed-Modality Benchmarks

Abstract

Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How do different alignment techniques (e.g., instruction tuning, RLHF) affect the reasoning capabilities of VLMs on mixed-modality benchmarks such as MMBench and LLaVA-Bench. 13 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do different alignment techniques (e.g., instruction tuning, RLHF) affect the reasoning capabilities of VLMs on mixed-modality benchmarks such as MMBench and LLaVA-Bench?

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