# Modeling Beyond MOS: Quality Assessment Models Must Integrate Context, Reasoning, and Multimodality

arXiv: https://arxiv.org/abs/2505.19696 · HTML: https://mlsanity.com/paper/2505.19696/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 105 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges](https://mlsanity.com/paper/2501.02189/) (2025)
- [PyTorch Image Quality: Metrics for Image Quality Assessment](https://mlsanity.com/paper/2208.14818/) (2022)
- [Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2403.11176/) (2024)
- [Subjective and Objective Quality Assessment of Image: A Survey](https://mlsanity.com/paper/1406.7799/) (2014)
- [A Survey on Image Quality Assessment: Insights, Analysis, and Future Outlook](https://mlsanity.com/paper/2502.08540/) (2025)
- [Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment](https://mlsanity.com/paper/2503.19295/) (2025)
- [Evaluating quality metrics through the lenses of psychophysical measurements of low-level vision](https://mlsanity.com/paper/2503.16264/) (2025)
- [A Multi-annotated and Multi-modal Dataset for Wide-angle Video Quality Assessment](https://mlsanity.com/paper/2501.12082/) (2025)
- [Semantically-Aware Game Image Quality Assessment](https://mlsanity.com/paper/2505.11724/) (2025)

## Built on by (most cited first, 2 of 2)

- [SASP: Strip-Aware Spatial Perception for Fine-Grained Bird Image Classification](https://mlsanity.com/paper/2505.24380/) (2025)
- [An Investigation of the NeurIPS and ICML 2025 Position Tracks](https://mlsanity.com/paper/2608.16894/) (2026)

## Abstract (arXiv)

This position paper argues that Mean Opinion Score (MOS), while historically foundational, is no longer sufficient as the sole supervisory signal for multimedia quality assessment models. MOS reduces rich, context-sensitive human judgments to a single scalar, obscuring semantic failures, user intent, and the rationale behind quality decisions. We contend that modern quality assessment models must integrate three interdependent capabilities: (1) context-awareness, to adapt evaluations to task-specific goals and viewing conditions; (2) reasoning, to produce interpretable, evidence-grounded justifications for quality judgments; and (3) multimodality, to align perceptual and semantic cues using vision-language models. We critique the limitations of current MOS-centric benchmarks and propose a roadmap for reform: richer datasets with contextual metadata and expert rationales, and new evaluation metrics that assess semantic alignment, reasoning fidelity, and contextual sensitivity. By reframing quality assessment as a contextual, explainable, and multimodal modeling task, we aim to catalyze a shift toward more robust, human-aligned, and trustworthy evaluation systems.