@inproceedings{yoon-park-2026-staged,
title = "Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit {QA} in {AI} Contact Centers",
author = "Yoon, Hyeonseop and
Park, Jeong-eun",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.26/",
pages = "330--342",
ISBN = "979-8-89176-478-1",
abstract = "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/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 reused across both domains, so inference stays a single retrieval pass with no query-time generation.On held-out query variants (in-distribution recipe reformulations) from two industrial domains, SLS is the dominant retrieval lever, lifting hybrid R@1 to 0.881/0.930 (+0.27/+0.34); the gain holds across all five retrievers we test. The win is the design, not the volume: at the same gpt-4.1-mini, SLS beats a budget-matched doc2query by +0.20/+0.32, and a cross-provenance control provides additional evidence of transfer across generated-query distributions; the embedding choice is secondary. Verified-unit answering also removes free-form generation{'}s unsupported-content surface (7{--}13{\%} vs. {\ensuremath{\approx}}0{\%}). We report this as an honest application study, including negative results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoon-park-2026-staged">
<titleInfo>
<title>Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyeonseop</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeong-eun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>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/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 reused across both domains, so inference stays a single retrieval pass with no query-time generation.On held-out query variants (in-distribution recipe reformulations) from two industrial domains, SLS is the dominant retrieval lever, lifting hybrid R@1 to 0.881/0.930 (+0.27/+0.34); the gain holds across all five retrievers we test. The win is the design, not the volume: at the same gpt-4.1-mini, SLS beats a budget-matched doc2query by +0.20/+0.32, and a cross-provenance control provides additional evidence of transfer across generated-query distributions; the embedding choice is secondary. Verified-unit answering also removes free-form generation’s unsupported-content surface (7–13% vs. \ensuremath\approx0%). We report this as an honest application study, including negative results.</abstract>
<identifier type="citekey">yoon-park-2026-staged</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>330</start>
<end>342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
%A Yoon, Hyeonseop
%A Park, Jeong-eun
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F yoon-park-2026-staged
%X 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/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 reused across both domains, so inference stays a single retrieval pass with no query-time generation.On held-out query variants (in-distribution recipe reformulations) from two industrial domains, SLS is the dominant retrieval lever, lifting hybrid R@1 to 0.881/0.930 (+0.27/+0.34); the gain holds across all five retrievers we test. The win is the design, not the volume: at the same gpt-4.1-mini, SLS beats a budget-matched doc2query by +0.20/+0.32, and a cross-provenance control provides additional evidence of transfer across generated-query distributions; the embedding choice is secondary. Verified-unit answering also removes free-form generation’s unsupported-content surface (7–13% vs. \ensuremath\approx0%). We report this as an honest application study, including negative results.
%U https://aclanthology.org/2026.groundlm-1.26/
%P 330-342
Markdown (Informal)
[Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers](https://aclanthology.org/2026.groundlm-1.26/) (Yoon & Park, GroundLM 2026)
ACL