基于声明门控的生成式搜索源风险审计
Claim-Gated Source-Risk Auditing for Generative Search
浏览论文内容
中文总结 AI 辅助
针对生成式搜索答案遗漏关键源关系的问题，提出声明门控审计规范，通过证据绑定与可执行记录契约，在合成测试中实现全组合覆盖与错误拒绝，并明确后续验证要求。
中文摘要 AI 辅助
生成式搜索的答案可以引用一个被支持的段落，却遗漏了会改变其解释的源关系。我们针对查询-源-答案三元组规定了一种声明门控审计。只有当关系证据、答案采纳、实质性和披露均被观察到时，遗漏才被解决；不完整的证据保持未解决状态，而非被视为独立性。该规范将此端点与引用支持和审查优先级区分开来，并将决策绑定到版本化的证据片段上。一个引用检查器使记录契约可执行。在一个详尽的合成套件上，它重现了所有81种三态谓词组合，并拒绝了192个故意构造的错误记录。通用防护基线和谓词消融将端点逻辑与缺失证据处理分离开来，而受控转换则检查支持分离和证据移除。这些是有限的契约一致性结果，而非检测器准确性或用户结果改善的证据。我们定义了建立语义有效性和部署效益仍所需的独立标注、留出评估和配对效用测试。
英文摘要
A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-source-answer tuple. An omission is resolved only when relationship evidence, answer adoption, materiality, and disclosure are all observed; incomplete evidence remains unresolved rather than being treated as independence. The specification separates this endpoint from citation support and review priority, and binds decisions to versioned evidence spans. A reference checker makes the record contract executable. On an exhaustive synthetic suite, it reproduces all 81 three-state predicate combinations and rejects 192 deliberately malformed records. Common-guard baselines and predicate ablations isolate endpoint logic from missing-evidence handling, while controlled transitions check support separation and evidence removal. These are finite contract-conformance results, not detector accuracy or evidence of improved user outcomes. We define the independent annotation, held-out evaluation, and paired utility tests still required to establish semantic validity and deployment benefit.
发表机构
- Google LLC（谷歌有限责任公司）
- Sony Corporate of America（索尼美国公司）
- Intuit Inc（Intuit公司）
机构由 AI 辅助整理，请以论文原文为准。
