cs.CVNov 19, 2026

Characterizing Age-Conditioned Affective Reasoning in Vision-Language Models

Authors: Shahriyar Zaman Ridoy, Azmine Toushik Wasi, Lin Gu, Ruogu Fang

Organizations: Department of Electrical and Computer Engineering, North South University, Bangladesh · CVSSP and PAI, University of Surrey, United Kingdom · Research Institute of Electrical Communication, Tohoku University, Japan · Department of Biomedical Engineering, Vanderbilt University, USA

Abstract

An age prompt can change how a vision-language model (VLM) rates the emotion evoked by an image. Does the change predict how people of different ages rate that same image? We evaluate 17 VLMs on 900 OASIS images using young-, middle-, and older-adult prompts and estimate image-specific age differences from ratings by 822 participants. Without an age cue, models closely track average human valence (median Pearson r=0.891r=0.891). Under an older-adult prompt, 16 of 17 models assign lower valence on average than under a young-adult prompt. Yet after adjusting for image pleasantness, correlations between model and human age effects range from −0.030-0.030 to 0.0930.093, against an estimated ceiling of 0.5950.595. The discrepancy is clearest on 54 sensitive images rated as pleasant. Across models, the older prompt reduces valence by 0.8450.845 points on average, while older participants rate these images 0.4430.443 points higher than younger participants. Providing human ratings from other images improves agreement on the direction of age differences, although image-specific fidelity remains modest on 600 held-out images (rpart=0.105r_{\mathrm{part}}=0.105). These results show why evaluations of demographic personalization in foundation models need human comparisons at the level of individual stimuli. Project page available at https://shahriyar-zaman.github.io/age-conditioned-emotion-reasoning/

Figures & tables

Appendix figures & tables97 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models

    Jan 27, 2026Filip Nowicki, Hubert Marciniak, Jakub Łączkowski +6Affective ComputingEmotion Recognition

  2. Frontier vision-language models have overtaken young adults at detecting AI-generated portraits -- but not their calibration

    Aug 31, 2026Sunwhi Kim, Sunyul Kim, Meounggun Jo +1VLM EvaluationVision-Language Models