@inproceedings{gupta-etal-2025-autosumm,
title = "{AUTOSUMM}: A Comprehensive Framework for {LLM}-Based Conversation Summarization",
author = "Gupta, Abhinav and
Singh, Devendra and
Cowan, Greig A and
Kadhiresan, N and
Srivastava, Siddharth and
Sriraja, Yagneswaran and
Mantri, Yoages Kumar",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.35/",
doi = "10.18653/v1/2025.acl-industry.35",
pages = "500--509",
ISBN = "979-8-89176-288-6",
abstract = "We present AUTOSUMM, a large language model (LLM)-based summarization system deployed in a regulated banking environment to generate accurate, privacy-compliant summaries of customer-advisor conversations. The system addresses challenges unique to this domain, including speaker attribution errors, hallucination risks, and short or low-information transcripts. Our architecture integrates dynamic transcript segmentation, thematic coverage tracking, and a domain specific multi-layered hallucination detection module that combines syntactic, semantic, and entailment-based checks. Human-in-the-loop feedback from over 300 advisors supports continuous refinement and auditability.Empirically, AUTOSUMM achieves a 94{\%} factual consistency rate and a significant reduction in hallucination rate. In production, 89{\%} of summaries required no edits, and only 1{\%} required major corrections. A structured model version management pipeline ensures stable upgrades with minimal disruption. We detail our deployment methodology, monitoring strategy, and ethical safeguards, showing how LLMs can be reliably integrated into high-stakes, regulated workflows."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2025-autosumm">
<titleInfo>
<title>AUTOSUMM: A Comprehensive Framework for LLM-Based Conversation Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devendra</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greig</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Cowan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">N</namePart>
<namePart type="family">Kadhiresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yagneswaran</namePart>
<namePart type="family">Sriraja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoages</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Mantri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>We present AUTOSUMM, a large language model (LLM)-based summarization system deployed in a regulated banking environment to generate accurate, privacy-compliant summaries of customer-advisor conversations. The system addresses challenges unique to this domain, including speaker attribution errors, hallucination risks, and short or low-information transcripts. Our architecture integrates dynamic transcript segmentation, thematic coverage tracking, and a domain specific multi-layered hallucination detection module that combines syntactic, semantic, and entailment-based checks. Human-in-the-loop feedback from over 300 advisors supports continuous refinement and auditability.Empirically, AUTOSUMM achieves a 94% factual consistency rate and a significant reduction in hallucination rate. In production, 89% of summaries required no edits, and only 1% required major corrections. A structured model version management pipeline ensures stable upgrades with minimal disruption. We detail our deployment methodology, monitoring strategy, and ethical safeguards, showing how LLMs can be reliably integrated into high-stakes, regulated workflows.</abstract>
<identifier type="citekey">gupta-etal-2025-autosumm</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.35</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.35/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>500</start>
<end>509</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AUTOSUMM: A Comprehensive Framework for LLM-Based Conversation Summarization
%A Gupta, Abhinav
%A Singh, Devendra
%A Cowan, Greig A.
%A Kadhiresan, N.
%A Srivastava, Siddharth
%A Sriraja, Yagneswaran
%A Mantri, Yoages Kumar
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F gupta-etal-2025-autosumm
%X We present AUTOSUMM, a large language model (LLM)-based summarization system deployed in a regulated banking environment to generate accurate, privacy-compliant summaries of customer-advisor conversations. The system addresses challenges unique to this domain, including speaker attribution errors, hallucination risks, and short or low-information transcripts. Our architecture integrates dynamic transcript segmentation, thematic coverage tracking, and a domain specific multi-layered hallucination detection module that combines syntactic, semantic, and entailment-based checks. Human-in-the-loop feedback from over 300 advisors supports continuous refinement and auditability.Empirically, AUTOSUMM achieves a 94% factual consistency rate and a significant reduction in hallucination rate. In production, 89% of summaries required no edits, and only 1% required major corrections. A structured model version management pipeline ensures stable upgrades with minimal disruption. We detail our deployment methodology, monitoring strategy, and ethical safeguards, showing how LLMs can be reliably integrated into high-stakes, regulated workflows.
%R 10.18653/v1/2025.acl-industry.35
%U https://aclanthology.org/2025.acl-industry.35/
%U https://doi.org/10.18653/v1/2025.acl-industry.35
%P 500-509
Markdown (Informal)
[AUTOSUMM: A Comprehensive Framework for LLM-Based Conversation Summarization](https://aclanthology.org/2025.acl-industry.35/) (Gupta et al., ACL 2025)
ACL
- Abhinav Gupta, Devendra Singh, Greig A Cowan, N Kadhiresan, Siddharth Srivastava, Yagneswaran Sriraja, and Yoages Kumar Mantri. 2025. AUTOSUMM: A Comprehensive Framework for LLM-Based Conversation Summarization. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 500–509, Vienna, Austria. Association for Computational Linguistics.