Comparison of Approaches to the Problem of Automatic Generation of Official Reply Letters using LLM
Main Article Content
Abstract
One of the key automation challenges for government agencies is the preparation of official response letters. This article presents an empirical comparison of two approaches to the automatic generation of official response letters: one based on templates defining the letter structure and one based on relevant letter examples selected using RAG. The original GovLetter dataset, which includes real-life business correspondence from government agencies in the Khanty-Mansi Autonomous Okrug – Yugra, was used as a basis. Generation was performed using a locally deployed open-source language model. The quality of the results was assessed according to 12 criteria using the Schema-Guided Reasoning (SGR) framework and the LLM-as-a-Judge methodology. The experimental results demonstrate that the example-based approach outperforms the template-based approach in most metrics, particularly in the accuracy of arguments, formal tone, and correct formatting. The obtained results confirm the potential of solutions based on document history for the effective automation of official response letter preparation.
Keywords:
Article Details
References
2. Qian Y., Zhang W.-N., Liu T. Harnessing the Power of Large Language Models for Empathetic Response Generation. arxiv:2310.05140. 2023. https://doi.org/10.48550/arXiv.2310.05140
3. Minkova L., López Espejel J., Djaidja T.E.T. et al. From Words to Workflows: Automating Business Processes. arXiv:2412.03446. 2024. https://doi.org/10.48550/arXiv.2412.03446
4. Xu W., Desai J., Wu F. et al. HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications. arXiv:2410.11239. 2024. https://doi.org/10.48550/arXiv.2410.11239
5. Li W., Soni S., Saha K. Emails by LLMs: A comparison of language in ai-generated and human-written emails // Proceedings of the ACM. 2025. https://doi.org/10.1145/3717867.371787
6. Shrivastava R., Sheikh A., Khan A. Cold Email Generator Using LLM. Preprint. https://doi.org/10.65521/ijacte.v14i1.382
7. Ray S., Pan R., Gu Z. et al. RAGServe: Fast Quality-Aware RAG Systems with Configuration Adaptation. arXiv:2412.10543. 2024. https://doi.org/10.48550/arXiv.2412.10543
8. Novelo R., Silva R.R., Bernardino J. A Literature Review of Personalized Large Language Models for Email Generation. https://doi.org/10.3390/fi17120536
9. Lehto T., Hinkka M. Discovering Business Area Effects to Process Mining Analysis Using Clustering and Influence Analysis// Conference proceedings. 2020. https://doi.org/10.1007/978-3-030-53337-3_18
10. Cerqueti R., Clemente G. P., Grassi R. Stratified communities in complex business networks. arXiv:1902.03854. 2019. https://doi.org/10.48550/arXiv.1902.03854
11. Thiergart J., Huber S., Übellacker T. Understanding emails and drafting responses–An approach using GPT-3. arXiv:2102.03062. 2021. https://doi.org/10.48550/arXiv.2102.03062
12. Jimenez-Gomez C.E., Cano-Carrillo J., Falcone Lanas F. Artificial Intelligence in Government // IEEE Computer. 2020. Vol. 53, No. 9. https://doi.org/10.1109/MC.2020.3010043
13. Barona J., Torres V. E., Defas Ayala R.V. La inteligencia artificial en los procesos de administración pública // Latam. 2023. Vol. 4, No. 6. https://doi.org/10.56712/latam.v4i6.1541
14. Aoki G. Large Language Models in Politics and Democracy: A Comprehensive Survey. arXiv:2412.04498. 2024. https://doi.org/10.48550/arXiv.2412.04498
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.