提出新检索目标CAR，精准获取当前有效权威文献。
Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge
- 设计CAR目标，确保检索结果包含最新权威文档
- 两阶段方法使TCA@5提升至0.975，显著优于单一检索
- 适合法律、医药、安全等需追踪权威变更的领域
在法律、药品监管和软件安全等领域，新权威可推翻旧权威，即使语义差异较大。本文提出CAR（Controlling Authority Retrieval）：针对语义锚点q，检索当前有效的权威前沿front(cl(A_k(q)))。不同于传统相关性排序argmax_d s(q, d)，CAR要求检索集R满足两个条件：前沿包含性（front(cl(A_k(q))) ⊆ R）与无被忽略的替代者（R外无超规文档）。定理4给出覆盖真实权威集的充要条件。命题2表明任意范围索引算法最坏情况下TCA@k ≤ phi(q) × R_anchor(q)，由对抗排列论证证明。在三个真实数据集上评估：安全通告（Dense TCA@5=0.270，两阶段0.975）、SCOTUS推翻对（Dense TCA=0.172，两阶段0.926）、FDA药品记录（Dense TCA=0.064，两阶段0.774）。GPT-4o-mini实验显示，密集RAG在39%存在补丁的查询中错误声称“未修补”，两阶段降至16%。四个基准数据集、领域适配器及单命令评分工具已开源于https://github.com/andremir/car-retrieval。
原文摘要 · Abstract (English)
In law, regulatory regimes for pharmaceuticals and software security, newer authorities can revoke older established ones even when semantically distant. We call this CAR: retrieving the currently active authority frontier for a semantic anchor q, that is, front(cl(A_k(q))). This differs from finding the most similar document by relevance score: argmax_d s(q, d). Theorem 4 characterizes when a set R truly covers the active authority set for q with TCA(R, q)=1, providing conditions necessary and sufficient for any retrieved set R: frontier inclusion (front(cl(A_k(q))) contained in R) and no-ignored-superseder (no superseding document exists in the corpus outside R). Proposition 2 shows that TCA@k <= phi(q) * R_anchor(q) in the worst case over any scope-indexed algorithm, proved by an adversarial permutation argument. We evaluated on three real-world datasets: security advisories (Dense TCA@5=0.270, two-stage 0.975), SCOTUS overruling pairs (Dense TCA=0.172, two-stage 0.926), and FDA drug records (Dense TCA=0.064, two-stage 0.774). A GPT-4o-mini experiment shows Dense RAG produces explicit "not patched" claims for 39% of queries where a patch exists; two-stage cuts this to 16%. Four benchmark datasets, domain adapters, and a single-command scorer are released at https://github.com/andremir/car-retrieval.
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。