# Language Model Prompt Selection via Simulation Optimization

arXiv: https://arxiv.org/abs/2404.08164 · HTML: https://mlsanity.com/paper/2404.08164/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 89 references that are in the map.
- First posted on arXiv 12 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models](https://mlsanity.com/paper/2306.03082/) (2023)
- [Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization](https://mlsanity.com/paper/2210.10199/) (2022)
- [A Hierarchical Neural Autoencoder for Paragraphs and Documents](https://mlsanity.com/paper/1506.01057/) (2015)
- [Sentence Bottleneck Autoencoders from Transformer Language Models](https://mlsanity.com/paper/2109.00055/) (2021)
- [Neural Contextual Bandits with UCB-based Exploration](https://mlsanity.com/paper/1911.04462/) (2019)
- [Singular Control of (Reflected) Brownian Motion: A Computational Method Suitable for Queueing Applications](https://mlsanity.com/paper/2312.11823/) (2023)
- [The (Surprising) Sample Optimality of Greedy Procedures for Large-Scale Ranking and Selection](https://mlsanity.com/paper/2303.02951/) (2023)
- [Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks](https://mlsanity.com/paper/2309.11651/) (2023)

## Built on by (most cited first, 3 of 3)

- [Hyperband-based Bayesian Optimization for Black-box Prompt Selection](https://mlsanity.com/paper/2412.07820/) (2024)
- [ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization](https://mlsanity.com/paper/2602.17867/) (2026)
- [Adaptive Simulation Experiment for LLM Policy Optimization](https://mlsanity.com/paper/2604.08779/) (2026)

## Abstract (arXiv)

With the advancement in generative language models, the selection of prompts has gained significant attention in recent years. A prompt is an instruction or description provided by the user, serving as a guide for the generative language model in content generation. Despite existing methods for prompt selection that are based on human labor, we consider facilitating this selection through simulation optimization, aiming to maximize a pre-defined score for the selected prompt. Specifically, we propose a two-stage framework. In the first stage, we determine a feasible set of prompts in sufficient numbers, where each prompt is represented by a moderate-dimensional vector. In the subsequent stage for evaluation and selection, we construct a surrogate model of the score regarding the moderate-dimensional vectors that represent the prompts. We propose sequentially selecting the prompt for evaluation based on this constructed surrogate model. We prove the consistency of the sequential evaluation procedure in our framework. We also conduct numerical experiments to demonstrate the efficacy of our proposed framework, providing practical instructions for implementation.