# Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers

arXiv: https://arxiv.org/abs/2609.00844 · HTML: https://mlsanity.com/paper/2609.00844/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions](https://mlsanity.com/paper/2506.09038/) (2025)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [Query expansion techniques for information retrieval: A survey](https://mlsanity.com/paper/1708.00247/) (2017)
- [Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering](https://mlsanity.com/paper/2010.12643/) (2020)
- [FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance](https://mlsanity.com/paper/1905.02851/) (2019)
- [DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers](https://mlsanity.com/paper/2502.18460/) (2025)
- [EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline](https://mlsanity.com/paper/2504.03598/) (2025)
- [A Financial Service Chatbot based on Deep Bidirectional Transformers](https://mlsanity.com/paper/2003.04987/) (2020)
- [Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents](https://mlsanity.com/paper/2502.17321/) (2025)
- [A System for Human-AI collaboration for Online Customer Support](https://mlsanity.com/paper/2301.12158/) (2023)
- [Is linguistically-motivated data augmentation worth it?](https://mlsanity.com/paper/2506.03593/) (2025)

## Abstract (arXiv)

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.