TY - GEN
T1 - LLM-PQA
T2 - 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024
AU - Li, Ziyu
AU - Zhao, Wenjie
AU - Katsifodimos, Asterios
AU - Hai, Rihan
PY - 2024
Y1 - 2024
N2 - The advent of Large Language Models (LLMs) provides an opportunity to change the way queries are processed, moving beyond the constraints of conventional SQL-based database systems. However, using an LLM to answer a prediction query is still challenging, since an external ML model has to be employed and inference has to be performed in order to provide an answer. This paper introduces LLM-PQA, a novel tool that addresses prediction queries formulated in natural language. LLM-PQA is the first to combine the capabilities of LLMs and retrieval-augmented mechanism for the needs of prediction queries by integrating data lakes and model zoos. This integration provides users with access to a vast spectrum of heterogeneous data and diverse ML models, facilitating dynamic prediction query answering. In addition, LLM-PQA can dynamically train models on demand, based on specific query requirements, ensuring reliable and relevant results even when no pre-trained model in a model zoo, available for the task.
AB - The advent of Large Language Models (LLMs) provides an opportunity to change the way queries are processed, moving beyond the constraints of conventional SQL-based database systems. However, using an LLM to answer a prediction query is still challenging, since an external ML model has to be employed and inference has to be performed in order to provide an answer. This paper introduces LLM-PQA, a novel tool that addresses prediction queries formulated in natural language. LLM-PQA is the first to combine the capabilities of LLMs and retrieval-augmented mechanism for the needs of prediction queries by integrating data lakes and model zoos. This integration provides users with access to a vast spectrum of heterogeneous data and diverse ML models, facilitating dynamic prediction query answering. In addition, LLM-PQA can dynamically train models on demand, based on specific query requirements, ensuring reliable and relevant results even when no pre-trained model in a model zoo, available for the task.
KW - data lake
KW - large language models
KW - model zoo
KW - prediction query
UR - http://www.scopus.com/inward/record.url?scp=85210030677&partnerID=8YFLogxK
U2 - 10.1145/3627673.3679210
DO - 10.1145/3627673.3679210
M3 - Conference contribution
AN - SCOPUS:85210030677
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 5239
EP - 5243
BT - CIKM 2024 - Proceedings of the 33rd ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery (ACM)
Y2 - 21 October 2024 through 25 October 2024
ER -