提出参与式溯源框架，审计AI总结中观点覆盖不均问题
Participatory provenance as representational auditing for AI-mediated public consultation
- 用参与式溯源分析观点在摘要中的分布情况
- 官方摘要平均覆盖率高于随机文本，但依赖嵌入模型
- 批判教育科技等区域覆盖差，改进方案可行且无需更长摘要
AI辅助公众咨询可加速大规模参与，但摘要可能更偏向部分意见。本文提出参与式溯源框架，用于审计从提交内容到摘要句子的语义覆盖分布。以加拿大2025年AI战略咨询为例（5,253条记录；2,861名参与者），官方摘要的平均覆盖度高于等长随机文本，但统计显著性取决于嵌入模型。低覆盖集中于特定语义区域，尤其是对教育技术的批评及对技术和监管的不信任；而多个覆盖较好的区域几乎没有记录达到操作阈值。在相同预算下，交叉训练的抽取式基准模型在保留样本上提升了平均和尾部覆盖率，表明无需更长摘要即可实现更好覆盖。咨询摘要应评估其语义覆盖分布，而不仅限于连贯性和事实支持。
原文摘要 · Abstract (English)
AI-assisted consultation can speed large-scale public engagement, but concise summaries may reflect some submissions more closely than others. This paper introduces participatory provenance, a framework for auditing how semantic coverage is distributed from submissions to summary sentences. Applied to two topics in Canada's 2025 AI Strategy consultation (5,253 records; 2,861 participants), official summaries had higher observed mean coverage than exact-length random text, although statistical significance depended on the embedding model. Low coverage concentrated in semantic regions, especially those centered on criticism of educational technology and distrust of technology and oversight, whereas few or no records crossed the operational threshold in several better-covered regions. Same-budget, cross-fitted extractive benchmarks improved mean and lower-tail coverage on held-out submissions, showing that better semantic coverage was feasible without longer summaries. Consultation summaries should be evaluated not only for coherence and factual support, but also for how coverage is distributed across the range of submitted views.
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。