mlsanityData to 7 Oct 2026

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

arXiv 2609.00844 ↗First posted 1 Sep 2026cs.CL cs.IRcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 1 Sep 2026.

Builds on

25 of 42 references.

References · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  4. 2017Selective Classification for Deep Neural Networkscited by 799
  5. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  6. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  7. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  8. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  9. 2020Autoregressive Entity Retrievalcited by 333
  10. 2022Teaching language models to support answers with verified quotescited by 290
  11. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 283
  12. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
13 more
  1. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  2. 2019Document Expansion by Query Predictioncited by 225
  3. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  4. 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questionscited by 129
  5. 2017Query expansion techniques for information retrieval: A surveycited by 44
  6. 2020Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answeringcited by 41
  7. 2019FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevancecited by 24
  8. 2025DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrieverscited by 19
  9. 2025EnrichIndex: Using LLMs to Enrich Retrieval Indices Offlinecited by 15
  10. 2020A Financial Service Chatbot based on Deep Bidirectional Transformerscited by 10
  11. 2025Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agentscited by 5
  12. 2023A System for Human-AI collaboration for Online Customer Supportcited by 3
  13. 2025Is linguistically-motivated data augmentation worth it?cited by 1

Built on by

Not cited yet.