Large Language Models

Users often need to integrate information from multiple data sources. This paper proposes autonomous systems that progressively discover and integrate relevant information from multiple data sources while requiring minimal expert intervention. The proposed systems leverage end users’ feedback to learn how to retrieve information relevant to each entity in a dataset from external data sources. Our empirical evaluation shows that our approach learns accurate strategies for delivering relevant information quickly.

As an alternative to manually writing mappings from entities to queries, one can learn these mappings progressively by leveraging end users’ feedback. We evaluate the use of parameter efficient techniques for leveraging a pretrained large language model (LLM) for this task of online query policy learning. We evaluate teqniques for parameter efficent fine-tuning of LLMs online. Also presented at the 2nd NeurIPS Table Representation Learning Workshop, December, 2023.