BABOONS: Black-Box Optimization of Data Summaries in Natural Language

BABOONS (BlAck BOx Optimization of Natural language data Summaries) optimizes text data summaries for an arbitrary, user-defined utility function. Primarily, it targets scenarios in which utility is evaluated via large language models. Users describe their utility function in natural language or provide a model, trained to score text summaries in a specific domain. BABOONS uses reinforcement learning to explore the space of possible descriptions. In each iteration, BABOONS generates summaries and evaluates their utility. To reduce data processing overheads during summary generation, BABOONS uses a proactive processing strategy that dynamically merges current with likely future queries for efficient processing. Also, BABOONS supports scenario-specific sampling and batch processing strategies. These mechanisms allow to scale processing to large data and item sets. The experiments show that BABOONS scales significantly better than baselines. Also, they show that summaries generated by BABOONS receive higher average grades from users in a large survey.

Automated summary

BABOONS optimizes text data summaries based on user-defined utility functions using reinforcement learning. It achieves high scalability and performance and receives high ratings from users in surveys.