arXiv cs.AI· Fengxian Ji, Jingpu Yang, Fan Zhang, Junhong Liang, Qian Jiang, Yuke Li, Jinri Guo, Rongxin Zhu, Zhuohan Xie·· 1 天前AI 评分31
交易价格能反映视觉偏好吗？基于多模态语言模型的诊断性研究
Do Transaction Prices Reflect Visual Preference? A Diagnostic Study with Multimodal Language Models
AI 导读
研究提出 MarketImage 诊断框架，用 266 组六图对比集与交易价格检验多模态语言模型能否恢复人类视觉偏好信号。仅 24.2% 图像对存在非并列价格方向，其中 34.7% 与人类多数判断一致；该区域内 HPSv2 以 66.4% Recoverable Accuracy 领先，Qwen 的预算与聚合变体落后于基线，GPT 接口提升在统计上未定论。
正文 · 原文
Abstract:Existing visual preference evaluation relies on costly human annotations or preference reward models, whereas online marketplace transaction prices are readily available and reflect real purchasing behavior, offering potential low-cost supervision. However, transaction prices conflate visual preferences with non-visual factors such as provenance, demand, and competition, making aggregate accuracy insufficient to distinguish model errors, unreliable price signals, and protocol confounds. To address this identifiability challenge, we introduce MarketImage, a diagnostic framework that identifies when transaction prices reflect visual preferences, where they fail, and whether multimodal language models can recover human-supported visual preference signals. MarketImage comprises three components: (i) MarketImageArt, 266 six-image comparison sets with transaction prices and price-blind human rankings; (ii) MarketImageLens, a tie-preserving protocol that partitions 3,990 within-set image pairs into price-human agreement, conflict, and price-tie regions while separately auditing presentation-order effects; and (iii) MarketValuator, six elicitation methods spanning direct comparison, independent scoring, budget constraints, and multi-agent aggregation to evaluate signal recovery by static visual scorers and three multimodal language models. Experiments show that only 24.2% of image pairs have a non-tied price direction, of which 34.7% agree with the human majority. Within this region, HPSv2 leads at 66.4% Recoverable Accuracy; Qwen's budgeted and aggregated variants trail baselines, while GPT interface gains remain statistically unresolved. Thus, transaction prices encode recoverable visual preferences only under limited conditions and should be treated as uncertain proxies rather than ground truth.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41358 [cs.AI] |
| (or arXiv:2610.41358v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41358 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fengxian Ji [view email]
[v1]
Fri, 30 Oct 2026 07:21:39 UTC (13,424 KB)
来源：arXiv cs.AI · arxiv.org