多域检索的认证域一致性：具有共形风险保证的无标签逐域污染控制
Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees
浏览论文内容
中文总结 AI 辅助
针对多域检索中错误域证据及污染控制问题，提出C3R控制层。基于风险控制预测集构建双分割方案，认证污染预算。通过实验验证其稳定性及有效性，能减少错误权威基础，且与冻结堆栈和重排器无关。
中文摘要 AI 辅助
在混合多个域的语料库上进行检索时，通常会返回相关但错误域的证据，排名指标会遗漏这些证据，共形风险控制边界也只能略微覆盖，无法涵盖最差的域。这项工作引入了C3R，这是一个可插入的控制层，它从推断的域后验和无查询时标签中，在可行的情况下认证每个域的污染预算，否则弃权而不是默默违反；在最难的域上，它保证减少，而不是紧密的边界。核心是基于风险控制预测集的双分割方案，其有限样本转移边界从推断域跨越到真实域，具有完全可估计的松弛度，支持异构预算，并可反转用于部署。总体有效性基于此边界和受控模拟；在一千次重新采样的校准中，证书从未违反（稳定性结果），而边际控制在每次抽取中都会违反污染最严重的域，并且在相同的认证污染下，软降级比最强的校准级联保留更多召回率。该方法在包括来自公共联邦法规的独立测试平台在内的开放测试平台上进行复制，并且一个由大语言模型判断的下游探针表明，错误权威的基础随着污染增加而上升，并在控制下下降。该层与冻结堆栈和重排器无关。
英文摘要
Retrieval over corpora that mix several domains often returns relevant but wrong-domain evidence that ranking metrics miss and that conformal risk control bounds only marginally, under-covering the worst domains. This work introduces C3R, a drop-in control layer that, from an inferred domain posterior and no query-time label, certifies a per-domain contamination budget where feasible and otherwise abstains rather than silently violating; on the hardest domains it guarantees a reduction, not a tight bound. The core is a two-split scheme built on risk-controlling prediction sets, whose finite-sample transfer bound crosses from the inferred to the true domain with fully estimable slack, supports heterogeneous budgets, and inverts for deployment. Population validity rests on this bound and a controlled simulation; across a thousand resampled calibrations the certificate never violates (a stability result) while marginal control violates the most-contaminated domain in every draw, and soft demotion retains more recall than the strongest calibrated cascade at equal certified contamination. The method replicates across open testbeds including an independent one from public federal regulations, and an LLM-judged downstream probe indicates wrong-authority grounding rises with contamination and falls under control. The layer is frozen-stack and reranker-agnostic.
发表机构
- Electric Power Research Institute (EPRI)（电力研究协会）
机构由 AI 辅助整理，请以论文原文为准。
