@inproceedings{diaz-morales-etal-2026-mcs,
title = "m{CS}-{LM}: Multimodal Customer Service and Incident Management Systems Based on Large Language Models",
author = "D{\'i}az-Morales, Carlos and
Checa-Rubio, Marcos and
Bernal-Beltr{\'a}n, Tom{\'a}s and
Pan, Ronghao and
Barb{\'a}chano, David and
Salas-Z{\'a}rate, Mar{\'i}a del Pilar and
Paredes-Valverde, Mario Andr{\'e}s and
Valencia-Garcia, Rafael",
editor = "Claramunt, German Rigau and
Gamallo, Pablo and
Mu{\~n}oz Guillena, Rafael and
Chiruzzo, Luis and
Mart{\'i}nez C{\'a}mara, Eugenio",
booktitle = "Proceedings of {LANLP}: Bridging {I}bero and {L}atin {A}merican {NLP} Communities",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lanlp-1.6/",
doi = "10.63317/3tcxy4bkn76p",
pages = "38--45",
abstract = "Customer service and incident management increasingly rely on multimodal evidence, combining text, images and audio. However, general-purpose models lack domain grounding, structured output control and reliability guarantees required in regulated enterprise environments, often leading to hallucinated responses and limiting their practical deployment. This paper presents mCS-LM, a multilingual multimodal framework that integrates Large Language Models (LLMs), Visual Language Models (VLMs), Audio Language Models (ALMs) and Retrieval-Augmented Generation (RAG) within a modular and traceable architecture tailored to customer service and incident management. The system introduces complementary processing flows: (i) perception modules for visual and audio understanding aligned with LLM-based reasoning, and (ii) structured report generation from multimodal evidence through supervised fine-tuning using QLoRA and efficient adaptation techniques. To mitigate hallucinations and improve factual reliability, the framework incorporates vector databases and multimodal RAG pipelines that retrieve domain-specific knowledge from external corporate sources. Formal structural schemas and validation mechanisms enforce output consistency and syntactic correctness. The platform is deployed as a web-based system with REST API integration, enabling scalable multimodal interaction across channels such as instant messaging, email and web chat. Experimental results demonstrate that multimodal generative models can be specialized for structured, domain-constrained enterprise tasks while maintaining computational viability and robustness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diaz-morales-etal-2026-mcs">
<titleInfo>
<title>mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Díaz-Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Checa-Rubio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomás</namePart>
<namePart type="family">Bernal-Beltrán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronghao</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Barbáchano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="given">del</namePart>
<namePart type="given">Pilar</namePart>
<namePart type="family">Salas-Zárate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="given">Andrés</namePart>
<namePart type="family">Paredes-Valverde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Valencia-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities</title>
</titleInfo>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Muñoz Guillena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugenio</namePart>
<namePart type="family">Martínez Cámara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Customer service and incident management increasingly rely on multimodal evidence, combining text, images and audio. However, general-purpose models lack domain grounding, structured output control and reliability guarantees required in regulated enterprise environments, often leading to hallucinated responses and limiting their practical deployment. This paper presents mCS-LM, a multilingual multimodal framework that integrates Large Language Models (LLMs), Visual Language Models (VLMs), Audio Language Models (ALMs) and Retrieval-Augmented Generation (RAG) within a modular and traceable architecture tailored to customer service and incident management. The system introduces complementary processing flows: (i) perception modules for visual and audio understanding aligned with LLM-based reasoning, and (ii) structured report generation from multimodal evidence through supervised fine-tuning using QLoRA and efficient adaptation techniques. To mitigate hallucinations and improve factual reliability, the framework incorporates vector databases and multimodal RAG pipelines that retrieve domain-specific knowledge from external corporate sources. Formal structural schemas and validation mechanisms enforce output consistency and syntactic correctness. The platform is deployed as a web-based system with REST API integration, enabling scalable multimodal interaction across channels such as instant messaging, email and web chat. Experimental results demonstrate that multimodal generative models can be specialized for structured, domain-constrained enterprise tasks while maintaining computational viability and robustness.</abstract>
<identifier type="citekey">diaz-morales-etal-2026-mcs</identifier>
<identifier type="doi">10.63317/3tcxy4bkn76p</identifier>
<location>
<url>https://aclanthology.org/2026.lanlp-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>38</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models
%A Díaz-Morales, Carlos
%A Checa-Rubio, Marcos
%A Bernal-Beltrán, Tomás
%A Pan, Ronghao
%A Barbáchano, David
%A Salas-Zárate, María del Pilar
%A Paredes-Valverde, Mario Andrés
%A Valencia-Garcia, Rafael
%Y Claramunt, German Rigau
%Y Gamallo, Pablo
%Y Muñoz Guillena, Rafael
%Y Chiruzzo, Luis
%Y Martínez Cámara, Eugenio
%S Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F diaz-morales-etal-2026-mcs
%X Customer service and incident management increasingly rely on multimodal evidence, combining text, images and audio. However, general-purpose models lack domain grounding, structured output control and reliability guarantees required in regulated enterprise environments, often leading to hallucinated responses and limiting their practical deployment. This paper presents mCS-LM, a multilingual multimodal framework that integrates Large Language Models (LLMs), Visual Language Models (VLMs), Audio Language Models (ALMs) and Retrieval-Augmented Generation (RAG) within a modular and traceable architecture tailored to customer service and incident management. The system introduces complementary processing flows: (i) perception modules for visual and audio understanding aligned with LLM-based reasoning, and (ii) structured report generation from multimodal evidence through supervised fine-tuning using QLoRA and efficient adaptation techniques. To mitigate hallucinations and improve factual reliability, the framework incorporates vector databases and multimodal RAG pipelines that retrieve domain-specific knowledge from external corporate sources. Formal structural schemas and validation mechanisms enforce output consistency and syntactic correctness. The platform is deployed as a web-based system with REST API integration, enabling scalable multimodal interaction across channels such as instant messaging, email and web chat. Experimental results demonstrate that multimodal generative models can be specialized for structured, domain-constrained enterprise tasks while maintaining computational viability and robustness.
%R 10.63317/3tcxy4bkn76p
%U https://aclanthology.org/2026.lanlp-1.6/
%U https://doi.org/10.63317/3tcxy4bkn76p
%P 38-45
Markdown (Informal)
[mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models](https://aclanthology.org/2026.lanlp-1.6/) (Díaz-Morales et al., LANLP 2026)
ACL
- Carlos Díaz-Morales, Marcos Checa-Rubio, Tomás Bernal-Beltrán, Ronghao Pan, David Barbáchano, María del Pilar Salas-Zárate, Mario Andrés Paredes-Valverde, and Rafael Valencia-Garcia. 2026. mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models. In Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities, pages 38–45, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).