Portrait of Amine Mhedhbi

Amine Mhedhbi

Associate Academic Member
Assistant Professor, Polytechnique Montréal, Department of Computer Engineering and Software Engineering
Polytechnique Montréal Montréal
Research Topics
Computer Systems
Data Science
Information Retrieval
Machine Learning Operations (MLOps)
Machine Learning Systems
Tabular Data

Publications

Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale
Priyan Vaithilingam
Frida-Cecilia Acosta-Parenteau
Daniel Lee
Elena L. Glassman
Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale
Priyan Vaithilingam
Frida-Cecilia Acosta-Parenteau
Daniel Lee
Elena L. Glassman
Towards Optimizing SQL Generation via LLM Routing
Mohammadhossein Malekpour
Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capabl… (see more)e large language models (LLMs) achieve strong accuracy for complex queries, they incur unnecessary latency and dollar cost for simpler ones. In this paper, we introduce the first LLM routing approach for Text-to-SQL, which dynamically selects the most cost-effective LLM capable of generating accurate SQL for each query. We present two routing strategies (score- and classification-based) that achieve accuracy comparable to the most capable LLM while reducing costs. We design the routers for ease of training and efficient inference. In our experiments, we highlight a practical and explainable accuracy-cost trade-off on the BIRD dataset.
Towards Optimizing SQL Generation via LLM Routing
Mohammadhossein Malekpour
Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capabl… (see more)e large language models (LLMs) achieve strong accuracy for complex queries, they incur unnecessary latency and dollar cost for simpler ones. In this paper, we introduce the first LLM routing approach for Text-to-SQL, which dynamically selects the most cost-effective LLM capable of generating accurate SQL for each query. We present two routing strategies (score- and classification-based) that achieve accuracy comparable to the most capable LLM while reducing costs. We design the routers for ease of training and efficient inference. In our experiments, we highlight a practical and explainable accuracy-cost trade-off on the BIRD dataset.