Reproducibility Study of Large Language Model Bayesian Optimization
By: Adam Rychert, Gasper Spagnolo, Evgenii Posashkov
Potential Business Impact:
Makes AI learn faster using smart text guesses.
In this reproducibility study, we revisit the LLAMBO framework of Daxberger et al. (2024), a prompting-based Bayesian optimization (BO) method that uses large language models as discriminative surrogates and acquisition optimizers via text-only interactions. We replicate the core Bayesmark and HPOBench experiments under the original evaluation protocol, but replace GPT-3.5 with the open-weight Llama 3.1 70B model used for all text encoding components. Our results broadly confirm the main claims of LLAMBO. Contextual warm starting via textual problem and hyperparameter descriptions substantially improves early regret behaviour and reduces variance across runs. LLAMBO's discriminative surrogate is weaker than GP or SMAC as a pure single task regressor, yet benefits from cross task semantic priors induced by the language model. Ablations that remove textual context markedly degrade predictive accuracy and calibration, while the LLAMBO candidate sampler consistently generates higher quality and more diverse proposals than TPE or random sampling. Experiments with smaller backbones (Gemma 27B, Llama 3.1 8B) yield unstable or invalid predictions, suggesting insufficient capacity for reliable surrogate behaviour. Overall, our study shows that the LLAMBO architecture is robust to changing the language model backbone and remains effective when instantiated with Llama 3.1 70B.
Similar Papers
An Exploratory Study of Bayesian Prompt Optimization for Test-Driven Code Generation with Large Language Models
Software Engineering
Helps computers write better, working code.
Benchmarking Large Language Models on Homework Assessment in Circuit Analysis
Computers and Society
Helps computers grade student homework accurately.
Large Scale Multi-Task Bayesian Optimization with Large Language Models
Machine Learning (CS)
AI learns from past jobs to do new ones better.