LLM Suggester: An AI-Driven Model Recommendation System for Task-Specific Large Language Model Selection

DOI

10.2991/978-94-6239-713-2_39How to use a DOI?

Keywords

AI Model Selection; Multi-Criteria Scoring; Web-Based Systems; Large Language Models; LLM Recommendation; Benchmark Analysis

Abstract

The increased development of Large Language Models (LLMs) has presented difficulties in choosing the most appropriate model to use in task-specific applications as they can be different in terms of performance, cost, latency, and safety. This paper will suggest the implementation of a web-based decision-support system, LLM Suggester, which will suggest the best LLM to implement based on a weighted multi-criteria decision-making (MCDM) method. The system measures the models based on benchmark datasets that include MMLU, Human Eval, and Truthful QA, and parameters of operation like cost per token, response latency and context window size. The given system was tested on 6 categories of tasks and 18 test cases. Experimental findings indicate that the system has a recommendation accuracy of 83.33% which is the ratio between system-selected models and expert-selected models. Findings show that the combination of benchmark scores and user preferences enhances the performance of model selection and decreases the complexity of decisions. The system offers scalable and data-driven solution of informed selection of LLM in practice.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shabbu Parveen
AU  - Harsh Kumar
AU  - Ankit Sharma
PY  - 2026
DA  - 2026/06/25
TI  - LLM Suggester: An AI-Driven Model Recommendation System for Task-Specific Large Language Model Selection
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 523
EP  - 536
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_39
DO  - 10.2991/978-94-6239-713-2_39
ID  - Parveen2026
ER  -