分阶段语言种子注入：AI客服中心经验证单元的接地查询扩展
Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
- OpenMined
- MaumAI, Inc.（MaumAI公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对AI客服中心问答的部署约束，提出分阶段语言种子注入（SLS）方法，通过接地槽配方生成查询变体并过滤，提升检索性能，降低不支持回答占比，为相关应用提供研究参考。
AI中文摘要：
AI客服中心（AICC）中的客户服务问答（QA）需满足部署约束：严格的语音热线延迟要求，以及不支持或错误自动回答的高成本。我们部署的系统仅从一组封闭的经验证QA单元中给出回答：逐字返回检索到的单元，或路由至澄清、弃权（不执行）或转交。索引通过分阶段语言种子注入（SLS）在离线阶段丰富：人员为每个单元编写接地于真实世界的槽配方，gpt-4.1-mini将其转化为变体，再由轻量级人工审核过滤。该方法在两个领域复用，因此推理阶段保持单次检索，无查询时生成。在两个工业领域的保留查询变体上，SLS将混合R@1提升至0.881/0.930（提升0.27/0.34），且在所有测试的5个检索器上均有提升。在相同的gpt-4.1-mini生成预算下，SLS比doc2query提升0.20/0.32，跨来源评估为生成查询分布的迁移提供了额外证据。经验证单元回答还消除了自由形式生成的不支持内容表面（7-13%对比约0%）。我们将此作为应用研究报告，包括负面结果。
英文摘要：
Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high cost for unsupported or wrong automatic answers. We deploy a system that answers only from a closed set of verified QA units: it returns a retrieved unit verbatim, or routes to clarify, abstain, or handoff. The index is enriched offline by staged linguistic seeding (SLS): a human authors a per-unit world-grounded slot recipe, gpt-4.1-mini renders it into variants, and a light human gate filters them. One methodology is reused across both domains, so inference stays a single retrieval pass with no query-time generation. On held-out query variants from two industrial domains, SLS lifts hybrid R@1 to 0.881/0.930 (+0.27/+0.34), with gains across all five retrievers tested. At the same gpt-4.1-mini generation budget, SLS beats doc2query by +0.20/+0.32, while cross-provenance evaluation provides additional evidence of transfer across generated-query distributions. Verified-unit answering also removes free-form generation's unsupported-content surface (7-13% versus approximately 0%). We report this as an application study, including negative results.
