@inproceedings{mohammadi-etal-2026-lingvarbench,
title = "{L}ing{V}ar{B}ench: Benchmarking {LLM}s on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts",
author = "Mohammadi, Seyedali and
Paldhe, Manas and
Chhabra, Amit and
Son, Youngseo and
Seshagiri, Vishal",
editor = {Matusevych, Yevgen and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en and
Aletras, Nikolaos},
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-industry.42/",
pages = "545--561",
ISBN = "979-8-89176-384-5",
abstract = "We study structured entity extraction from phone-call transcripts in customer-support and healthcare settings, where annotation is costly, and data access is limited by privacy and consent. Existing methods degrade under disfluencies, interruptions, and speaker overlap, yet large real-call corpora are rarely shareable. We introduce LingVarBench, a benchmark and semantic synthetic data generation pipeline that generates linguistically varied training data via (1) LLM-sampled entity values, (2) curated linguistic verbalization patterns covering diverse disfluencies and entity-specific readout styles, and (3) a value{--}transcript consistency filter. Using this dataset, DSPy{'}s SIMBA automatically synthesizes and optimizes extraction prompts, reducing manual prompt engineering and targeting robustness to verbal variation. On real customer transcripts, prompts optimized solely on LingVarBench outperform zero-shot baselines and match or closely approach human-tuned prompts for structured entities such as ZIP code, date of birth, and name (F1 approximately 94-95 percent). For subjective questionnaire items, optimized prompts substantially improve over zero-shot performance and approach human-tuned prompts. LingVarBench offers a practical and cost-efficient path to deployment in a direct-answer setting, with real annotations later enabling additional refinement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohammadi-etal-2026-lingvarbench">
<titleInfo>
<title>LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seyedali</namePart>
<namePart type="family">Mohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manas</namePart>
<namePart type="family">Paldhe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Chhabra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngseo</namePart>
<namePart type="family">Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishal</namePart>
<namePart type="family">Seshagiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yevgen</namePart>
<namePart type="family">Matusevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-384-5</identifier>
</relatedItem>
<abstract>We study structured entity extraction from phone-call transcripts in customer-support and healthcare settings, where annotation is costly, and data access is limited by privacy and consent. Existing methods degrade under disfluencies, interruptions, and speaker overlap, yet large real-call corpora are rarely shareable. We introduce LingVarBench, a benchmark and semantic synthetic data generation pipeline that generates linguistically varied training data via (1) LLM-sampled entity values, (2) curated linguistic verbalization patterns covering diverse disfluencies and entity-specific readout styles, and (3) a value–transcript consistency filter. Using this dataset, DSPy’s SIMBA automatically synthesizes and optimizes extraction prompts, reducing manual prompt engineering and targeting robustness to verbal variation. On real customer transcripts, prompts optimized solely on LingVarBench outperform zero-shot baselines and match or closely approach human-tuned prompts for structured entities such as ZIP code, date of birth, and name (F1 approximately 94-95 percent). For subjective questionnaire items, optimized prompts substantially improve over zero-shot performance and approach human-tuned prompts. LingVarBench offers a practical and cost-efficient path to deployment in a direct-answer setting, with real annotations later enabling additional refinement.</abstract>
<identifier type="citekey">mohammadi-etal-2026-lingvarbench</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-industry.42/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>545</start>
<end>561</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts
%A Mohammadi, Seyedali
%A Paldhe, Manas
%A Chhabra, Amit
%A Son, Youngseo
%A Seshagiri, Vishal
%Y Matusevych, Yevgen
%Y Eryiğit, Gülşen
%Y Aletras, Nikolaos
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-384-5
%F mohammadi-etal-2026-lingvarbench
%X We study structured entity extraction from phone-call transcripts in customer-support and healthcare settings, where annotation is costly, and data access is limited by privacy and consent. Existing methods degrade under disfluencies, interruptions, and speaker overlap, yet large real-call corpora are rarely shareable. We introduce LingVarBench, a benchmark and semantic synthetic data generation pipeline that generates linguistically varied training data via (1) LLM-sampled entity values, (2) curated linguistic verbalization patterns covering diverse disfluencies and entity-specific readout styles, and (3) a value–transcript consistency filter. Using this dataset, DSPy’s SIMBA automatically synthesizes and optimizes extraction prompts, reducing manual prompt engineering and targeting robustness to verbal variation. On real customer transcripts, prompts optimized solely on LingVarBench outperform zero-shot baselines and match or closely approach human-tuned prompts for structured entities such as ZIP code, date of birth, and name (F1 approximately 94-95 percent). For subjective questionnaire items, optimized prompts substantially improve over zero-shot performance and approach human-tuned prompts. LingVarBench offers a practical and cost-efficient path to deployment in a direct-answer setting, with real annotations later enabling additional refinement.
%U https://aclanthology.org/2026.eacl-industry.42/
%P 545-561
Markdown (Informal)
[LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts](https://aclanthology.org/2026.eacl-industry.42/) (Mohammadi et al., EACL 2026)
ACL