---
title: "mCS-LM — paper by Díaz-Morales et al. (2026)"
description: "Customer service and incident handling now involve mixed evidence such as written complaints, photos of damage and voice… 19 references."
authors: ["Carlos Díaz-Morales", "Marcos Checa-Rubio", "Tomás Bernal-Beltrán", "Ronghao Pan", "David Barbáchano", "María del Pilar Salas-Zárate", "Mario Andrés Paredes-Valverde", "Rafael Valencia-Garcia"]
year: 2026
venue: "Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities"
source: "https://aclanthology.org/2026.lanlp-1.6/"
doi: "10.63317/3tcxy4bkn76p"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/morales-2026-mcs-lm-multimodal-customer-service/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/morales-2026-mcs-lm-multimodal-customer-service/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/) / mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models

# mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models

**Authors:** Carlos Díaz-Morales, Marcos Checa-Rubio, [Tomás Bernal-Beltrán](https://md.research.elamur.ai/free/en/authors/tomas-bernal-beltran/), [Ronghao Pan](https://md.research.elamur.ai/free/en/authors/ronghao-pan/), David Barbáchano, María del Pilar Salas-Zárate, Mario Andrés Paredes-Valverde and [Rafael Valencia-Garcia](https://md.research.elamur.ai/free/en/authors/rafael-valencia-garcia/) · **Year:** 2026 · **Venue:** [Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities](https://md.research.elamur.ai/free/en/venues/lanlp/) ([LANLP: Bridging Ibero and Latin American NLP Communities 2026](https://md.research.elamur.ai/free/en/venues/lanlp/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lanlp-1.6/) · [PDF](https://aclanthology.org/2026.lanlp-1.6.pdf) · [DOI 10.63317/3tcxy4bkn76p](https://doi.org/10.63317/3tcxy4bkn76p) · [OpenAlex](https://openalex.org/W7166569973)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Customer service and incident handling now involve mixed evidence such as written complaints, photos of damage and voice recordings. Off-the-shelf generative models often hallucinate, rarely follow domain-specific output formats, and are costly to run, which especially limits SMEs. mCS-LM is a multilingual framework, covering Spanish and English among others, that combines LLMs, VLMs and ALMs with multimodal RAG in a modular, traceable design. Perception modules map text, image and audio inputs into a shared representation. A retrieval layer backed by vector databases supplies corporate knowledge such as policies and manuals. A control module classifies user intent before generation and restricts outputs through schemas, predefined prompts, validation and constrained decoding. Structured incident reports come from models adapted with QLoRA. The platform is delivered via a web interface and REST APIs, with an agent dashboard for KPIs and human oversight. The authors claim such models can be specialized for constrained enterprise tasks at manageable cost. However, the paper is mainly architectural, and benchmarking against baselines is still ongoing.

## Key points
- Integrates LLM, VLM and ALM perception modules with multimodal RAG over vector databases built from enterprise documents (policy texts, procedural manuals, internal databases).
- Hallucination control combines intent classification and routing before decoding, domain schemas, validation layers and controlled decoding. Report generation uses supervised fine-tuning with QLoRA.
- The system is deployed as a web-based microservices system with REST API access for instant messaging, email and web chat. A separate agent dashboard tracks incidents, intents, resolution status and escalations.
- The consortium includes Panel Sistemas S.L., the TECNOMOD group (University of Murcia), Medio Melón S.A. and Instituto Tecnológico Teziutlán, under international cooperation project UNI-20240017.
- No quantitative scores are given in the available text. Validation with customer-service practitioners on real enterprise incident data is ongoing, and baseline comparisons are left for future work.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Universidad de Murcia](https://md.research.elamur.ai/free/en/universities/universidad-de-murcia/) — University, Murcia, Spain · 5 works · 3 citations

Also on the byline: [Tecnológico Nacional de México](https://ror.org/00davry38) · [Instituto Tecnológico Superior de Teziutlán](https://ror.org/035c3rc79).

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: 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. Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{diazmorales2026mcs,
  title = {{mCS-LM: Multimodal Customer Service and Incident Management Systems Based on Large Language Models}},
  author = {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},
  booktitle = {Proceedings of LANLP: Bridging Ibero and Latin American NLP Communities},
  year = {2026},
  doi = {10.63317/3tcxy4bkn76p},
  url = {https://doi.org/10.63317/3tcxy4bkn76p}
}
```

- [← previous MCLE-Mol: Empowering LLM with Molecular Comprehension and Low-Cost Continual Evolution for Interpretable Property Prediction](https://md.research.elamur.ai/free/en/papers/pu-2026-mcle-mol-empowering-llm-molecular/)
- [next → MD_NLP: Reconstructing an Australian English Heritage Dialect Corpus from the Mitchell-Delbridge Recordings through LLM-Assisted Speaker Attribution](https://md.research.elamur.ai/free/en/papers/coats-2026-md-nlp-reconstructing-australian-english/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/)

## References

19 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. James Gung, Emily Moeng, Wesley Rose, Arshit Gupta, Yi Zhang, and Saab Mansour. 2023. Natcs: Eliciting natural customer support dialogues. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9652– 9677. [find](https://scholar.google.com/scholar?q=James+Gung%2C+Emily+Moeng%2C+Wesley+Rose%2C+Arshit+Gupta%2C+Yi+Zhang%2C+and+Saab+Mansour%2E+2023%2E+Natcs%3A+Eliciting+natural+customer+support+dialogues%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)
2. Mohammad Mahdi Abootorabi, Amirhosein Zobeiri, Mahdi Dehghani, Mohammadali Mohammadkhani, Bardia Mohammadi, Omid Ghahroodi, Mahdieh Soleymani Baghshah, and Ehsaneddin Asgari. 2025. Ask in any modality: A comprehensive survey on multimodal retrieval-augmented generation. Findings of the Association f… [find](https://scholar.google.com/scholar?q=Mohammad+Mahdi+Abootorabi%2C+Amirhosein+Zobeiri%2C+Mahdi+Dehghani%2C+Mohammadali+Mohammadkhani%2C+Bardia+Mohammadi%2C+Omid+Ghahroodi%2C+Mahdieh+Soleymani+Baghshah%2C+and+Ehsaneddin+Asgari%2E+2025%2E+Ask+in+any+modality)
3. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. [Deep residual learning for image recognition](https://md.research.elamur.ai/free/en/papers/he-2015-deep-residual-learning-image-recognition/). In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
4. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. [Lora: Low-rank a…](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/)
5. Conference on Intelligent User Interfaces, pages 99–101. [find](https://scholar.google.com/scholar?q=Conference+on+Intelligent+User+Interfaces%2C+pages+99%E2%80%93101%2E)
6. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2025. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems, 43(2):…
7. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.
8. Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. 2024. A comprehensive survey of continual learning: Theory, method and application. IEEE transactions on pattern analysis and machine intelligence, 46(8):5362–5383. [find](https://scholar.google.com/scholar?q=Liyuan+Wang%2C+Xingxing+Zhang%2C+Hang+Su%2C+and+Jun+Zhu%2E+2024%2E+A+comprehensive+survey+of+continual+learning%3A+Theory%2C+method+and+application%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+4)
9. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–9474.
10. Anbang Xu, Zhe Liu, Yufan Guo, Vibha Sinha, and Rama Akkiraju. 2017. A new chatbot for customer service on social media. In Proceedings of the 2017 CHI conference on human factors in computing systems, pages 3506–3510. [find](https://scholar.google.com/scholar?q=Anbang+Xu%2C+Zhe+Liu%2C+Yufan+Guo%2C+Vibha+Sinha%2C+and+Rama+Akkiraju%2E+2017%2E+A+new+chatbot+for+customer+service+on+social+media%2E+In+Proceedings+of+the+2017+CHI+conference+on+human+factors+in+computing+systems)
11. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. [Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In International conference on machine learning, pages 19730– 19742. PMLR.
12. Chih-Kai Yang, Neo S Ho, and Hung-yi Lee. 2025. [Towards holistic evaluation of large audio-language models: A comprehensive survey](https://md.research.elamur.ai/free/en/papers/yang-2025-holistic-evaluation-large-audio-language/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 10155–10181.
13. Alexandra Sasha Luccioni, Sylvain Viguier, and Anne-Laure Ligozat. 2023. Estimating the carbon footprint of bloom, a 176b parameter language model. Journal of machine learning research, 24(253):1–15. [find](https://scholar.google.com/scholar?q=Alexandra+Sasha+Luccioni%2C+Sylvain+Viguier%2C+and+Anne%2DLaure+Ligozat%2E+2023%2E+Estimating+the+carbon+footprint+of+bloom%2C+a+176b+parameter+language+model%2E+Journal+of+machine+learning+research%2C+24%28253%29%3A1%E2%80%9315%2E)
14. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. 2023. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223, 1(2).
15. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8763. Pm…
16. Michael Shumanov and Lester Johnson. 2021. Making conversations with chatbots more personalized. Computers in human behavior, 117:106627. [find](https://scholar.google.com/scholar?q=Michael+Shumanov+and+Lester+Johnson%2E+2021%2E+Making+conversations+with+chatbots+more+personalized%2E+Computers+in+human+behavior%2C+117%3A106627%2E)
17. Emanuel Stoeckli, Christian Dremel, and Falk Ue-bernickel. 2018. Exploring characteristics and transformational capabilities of insurtech innovations to understand insurance value creation in a digital world. Electronic markets, 28(3):287–305. [find](https://scholar.google.com/scholar?q=Emanuel+Stoeckli%2C+Christian+Dremel%2C+and+Falk+Ue%2Dbernickel%2E+2018%2E+Exploring+characteristics+and+transformational+capabilities+of+insurtech+innovations+to+understand+insurance+value+creation+in+a+digita)
18. Yi Su, Jisheng Bai, Qisheng Xu, Kele Xu, and Yong Dou. 2025. Audio-language models for audio-centric tasks: A survey. arXiv preprint arXiv:2501.15177. — [arXiv:2501.15177](https://arxiv.org/abs/2501.15177) [find](https://scholar.google.com/scholar?q=Yi+Su%2C+Jisheng+Bai%2C+Qisheng+Xu%2C+Kele+Xu%2C+and+Yong+Dou%2E+2025%2E+Audio%2Dlanguage+models+for+audio%2Dcentric+tasks%3A+A+survey%2E+arXiv+preprint+arXiv%3A2501%2E15177%2E+%E2%80%94+%5BarXiv%3A2501%2E15177%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2501%2E1)
19. Xin Sun, Jos A Bosch, Jan De Wit, and Emiel Krahmer. 2023. Human-in-the-loop interaction for continuously improving generative model in conversational agent for behavioral intervention. In Companion Proceedings of the 28th International [find](https://scholar.google.com/scholar?q=Xin+Sun%2C+Jos+A+Bosch%2C+Jan+De+Wit%2C+and+Emiel+Krahmer%2E+2023%2E+Human%2Din%2Dthe%2Dloop+interaction+for+continuously+improving+generative+model+in+conversational+agent+for+behavioral+intervention%2E+In+Companion+P)

*Updated 1 November 2026*