9 papers
Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning
Trinh Pham, Viet Huynh, Hongzhi Yin +2
The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released mo…
An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data
Trinh Pham, Thanh Tam Nguyen, Viet Huynh +2
Recent advances in large language models have strengthened Text2SQL systems that translate natural language questions into database queries. A persistent deployment challenge is to…
A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback
Thanh Dat Hoang, Thanh Trung Huynh, Matthias Weidlich +4
Text2SQL, the task of generating SQL queries from natural language text, is a critical challenge in data engineering. Recently, Large Language Models (LLMs) have demonstrated super…
Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers
Thanh Dat Hoang, Thanh Tam Nguyen, Thanh Trung Huynh +2
Most modern Text2SQL systems prompt large language models (LLMs) with entire schemas -- mostly column information -- alongside the user's question. While effective on small databas…
Efficient Multimodal Streaming Recommendation via Expandable Side Mixture-of-Experts
Yunke Qu, Liang Qu, Tong Chen +2
Streaming recommender systems (SRSs) are widely deployed in real-world applications, where user interests shift and new items arrive over time. As a result, effectively capturing u…
Proxy Model-Guided Reinforcement Learning for Client Selection in Federated Recommendation
Liang Qu, Jianxin Li, Wei Yuan +3
Federated recommender systems have emerged as a promising privacy-preserving paradigm, enabling personalized recommendation services without exposing users' raw data. By keeping da…