Conference paper · 2026 · Open access

FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support

Chenyan Jiang, Juntao Yang, Min Liu, Huawei Wang

International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 182–186 · Published 1 August 2026 · DOI 10.1109/icaita71179.2026.11737058

Open full textCite this paper

In brief

“FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support” is a 2026 conference paper by Chenyan Jiang and 3 co-authors, published in International Conference on Artificial Intelligence Technologies and Applications (ICAITA). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Artificial Intelligence Technologies and Applications (ICAITA).

Citations
0
References
10
Authors
4

Abstract

Fire rescue command is a high-stakes decision-making task that requires rapid interpretation of uncertain incident information, integration of heterogeneous operational data, and formulation of tactically coherent response plans. Conventional dispatch and command workflows often depend on fragmented information systems and individual experience, which may reduce consistency, traceability, and information coverage during time-critical operations. This paper proposes FireLLM-DSS, a retrieval-augmented large language model framework for real-time fire rescue decision support. The framework integrates incident reports, building attributes, weather and traffic conditions, resource inventories, standard operating procedures, and historical response cases into a fire rescue knowledge base. A hybrid retrieval module combines semantic search, keyword matching, and scenario-specific rule filtering to select relevant evidence before generation. A constraint-aware generation module then produces structured recommendations for resource dispatch, tactical priorities, risk warnings, and evidence references. To support reproducible evaluation before access to authorized operational records, this study constructs a scenario-based synthetic benchmark containing 960 fire rescue cases and 240 knowledge items. On the 144-case synthetic test split, FireLLM-DSS achieves 93.09% evidence coverage, 91.50% key-factor coverage, an expert-utility proxy score of 90.28, and a 2.24% unsupported-claim rate, with an average decision response time of 3.396 s. The proposed framework provides a practical research foundation for applying retrieval-augmented language models to fire rescue command while preserving evidence traceability and operational accountability.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Jiang, C., Yang, J., Liu, M., & Wang, H. (2026). FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support. International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 182–186. https://doi.org/10.1109/icaita71179.2026.11737058

MLA 9

Jiang, Chenyan, et al. “FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support.” International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 2026, pp. 182–186. https://doi.org/10.1109/icaita71179.2026.11737058.

Chicago

Jiang, Chenyan, Juntao Yang, Min Liu, and Huawei Wang. 2026. “FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support.” International Conference on Artificial Intelligence Technologies and Applications (ICAITA): 182–186. https://doi.org/10.1109/icaita71179.2026.11737058.

Harvard

Jiang, C. et al. (2026) ‘FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support’, International Conference on Artificial Intelligence Technologies and Applications (ICAITA), pp. 182–186. doi:10.1109/icaita71179.2026.11737058.

IEEE

C. Jiang, J. Yang, M. Liu, and H. Wang, “FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support,” International Conference on Artificial Intelligence Technologies and Applications (ICAITA), pp. 182–186, 2026, doi: 10.1109/icaita71179.2026.11737058.

BibTeX

@inproceedings{jiang2026firellm,
  title     = {{FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support}},
  author    = {Jiang, Chenyan and Yang, Juntao and Liu, Min and Wang, Huawei},
  booktitle = {International Conference on Artificial Intelligence Technologies and Applications (ICAITA)},
  year      = {2026},
  pages     = {182--186},
  doi       = {10.1109/icaita71179.2026.11737058},
  url       = {https://doi.org/10.1109/icaita71179.2026.11737058}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Social Sciences › Safety Research › Safety and Risk Management

  • decision support
  • retrieval-augmented generation
  • large language models
  • hybrid retrieval
  • synthetic benchmark
  • evidence traceability
  • emergency dispatch

Work with this paper

Most-cited papers in Social Sciences

All highly cited Social Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Jiang, C., Yang, J., Liu, M., & Wang, H. (2026). FireLLM-DSS: A Retrieval-Augmented Large Language Model Framework for Real-Time Fire Rescue Decision Support. International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 182–186. https://doi.org/10.1109/icaita71179.2026.11737058

How many times has this paper been cited?

0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Conference on Artificial Intelligence Technologies and Applications (ICAITA): sign in and open the full text from this page.

Who wrote this paper?

Chenyan Jiang, Juntao Yang, Min Liu, Huawei Wang.

What is the DOI of this paper?

10.1109/icaita71179.2026.11737058, permanently at https://doi.org/10.1109/icaita71179.2026.11737058. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.