Language-Based Bayesian Optimization Research Assistant (BORA)
This addresses the challenge of slow experimental optimization for scientists, offering a hybrid approach that mitigates human bias and leverages literature insights, though it is incremental as it builds on existing Bayesian optimization methods.
The paper tackles the problem of high-dimensional, non-convex optimization in scientific experiments by integrating Large Language Models (LLMs) with Bayesian optimization to provide context-aware suggestions, resulting in substantial performance boosts in real-world tasks.
Many important scientific problems involve multivariate optimization coupled with slow and laborious experimental measurements. These complex, high-dimensional searches can be defined by non-convex optimization landscapes that resemble needle-in-a-haystack surfaces, leading to entrapment in local minima. Contextualizing optimizers with human domain knowledge is a powerful approach to guide searches to localized fruitful regions. However, this approach is susceptible to human confirmation bias and it is also challenging for domain experts to keep track of the rapidly expanding scientific literature. Here, we propose the use of Large Language Models (LLMs) for contextualizing Bayesian optimization (BO) via a hybrid optimization framework that intelligently and economically blends stochastic inference with domain knowledge-based insights from the LLM, which is used to suggest new, better-performing areas of the search space for exploration. Our method fosters user engagement by offering real-time commentary on the optimization progress, explaining the reasoning behind the search strategies. We validate the effectiveness of our approach on synthetic benchmarks with up to 15 independent variables and demonstrate the ability of LLMs to reason in four real-world experimental tasks where context-aware suggestions boost optimization performance substantially.