Multimodal Reasoning in Aligned LLMs: SFT, RLHF, and DPO Effects on HumanEval-V

Abstract

Abstract: This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How do different alignment techniques (e.g., SFT, RLHF, DPO) impact the multimodal reasoning capabilities of LLMs on HumanEval-V compared to their performance on text-only benchmarks like HumanEval. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do different alignment techniques (e.g., SFT, RLHF, DPO) impact the multimodal reasoning capabilities of LLMs on HumanEval-V compared to their performance on text-only benchmarks like 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