不同品牌在AI中可见性差异大，需针对实体校准偏差。
Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration
- 构建十维实体偏差映射框架，区分原始与验证提及。
- 发现头部品牌幻觉引用率比三线品牌高14.82个百分点。
- 适合关注AI偏见、品牌传播与合规风险的研究者。
AI问答系统日益决定品牌与组织在用户面前的呈现方式。现有方法仅依赖提及频率或引用次数，但本文指出这些聚合指标不足，因不同实体存在系统性可见性偏差。提出实体级偏差映射（PEBM）框架，包含十维维度，区分原始提及与验证提及。识别出四种失效模式：（1）低曝光实体因知识图谱覆盖弱而被忽视；（2）大型品牌陷入“品牌幻觉悖论”——模型熟悉度导致更易生成看似合理但错误的补全；（3）CEE类实体在知识图谱、命名实体识别和实体链接环节存在结构性断层；（4）参数化与检索增强记忆更新周期不一致。大规模实证研究（n=100匈牙利B2B企业，1,400次探测，2,062个来源）显示，一级品牌幻觉引用率达52.69%，三级品牌为37.87%（+14.82个百分点；p=1.67e-11），支持幻觉悖论。监管语境下幻觉率升至56.77%，显著高于基线37.59%（+19.2个百分点）。发现拒绝诱导型幻觉加剧：在合规场景中，智能质量过滤反而加速幻觉生成。提出“幽灵制图”作为统一机制：位于稀疏潜在区域的实体会生成自信输出，基于邻近密集区域插值，形成二维幻觉空间（虚假存在性与冻结表征）。
原文摘要 · Abstract (English)
AI-mediated answer systems increasingly determine how brands and organizations are represented to users. Existing approaches reduce visibility to mention rate or citation frequency. This paper argues that aggregate metrics are insufficient because entities exhibit systematically different AI visibility error profiles. We introduce Per-Entity Bias Mapping (PEBM): a ten-dimensional framework distinguishing raw from verified mentions. Three failure modes are identified: (1) underrepresented entities suffer invisibility due to weak knowledge graph presence; (2) large entities suffer the Brand Hallucination Paradox -- model familiarity creates stronger surfaces for plausible but incorrect completions; (3) CEE entities face a structural infrastructure gap across knowledge graphs, NER, and entity linking. A fourth dimension, Parametric-Retrieval Lag Asymmetry, describes divergence between retrieval-augmented and parametric memory update cycles. A full-scale empirical study (n=100 Hungarian B2B entities, 1,400 probe runs, 2,062 sources) finds Tier 1 brands produce 52.69% fabricated citations versus 37.87% for Tier 3 entities (+14.82 pp; p=1.67e-11), supporting the Brand Hallucination Paradox. Regulatory-framed queries elevate fabrication to 56.77% versus 37.59% baseline (+19.2 pp). We identify rejection-induced confabulation escalation: agentic quality filters function as hallucination accelerators in compliance contexts. We introduce ghost cartography as a unifying mechanism: entities in sparse latent regions produce confident output interpolated from neighboring dense regions, yielding a two-dimensional confabulation space (fabricated presence vs. frozen representation).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。