# InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

arXiv: https://arxiv.org/abs/2306.03082 · HTML: https://mlsanity.com/paper/2306.03082/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization](https://mlsanity.com/paper/2212.12017/) (2022)
- [Bayesian Optimization in a Billion Dimensions via Random Embeddings](https://mlsanity.com/paper/1301.1942/) (2013)
- [Instruction Induction: From Few Examples to Natural Language Task Descriptions](https://mlsanity.com/paper/2205.10782/) (2022)
- [Stochastic Zeroth-order Optimization in High Dimensions](https://mlsanity.com/paper/1710.10551/) (2017)

## Built on by (most cited first, 30 of 68)

- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs](https://mlsanity.com/paper/2404.16873/) (2024)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks](https://mlsanity.com/paper/2403.03792/) (2024)
- [Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement](https://mlsanity.com/paper/2405.15973/) (2024)
- [Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld](https://mlsanity.com/paper/2311.16714/) (2023)
- [AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors](https://mlsanity.com/paper/2310.17419/) (2023)
- [Efficient Prompting Methods for Large Language Models: A Survey](https://mlsanity.com/paper/2404.01077/) (2024)
- [Are Large Language Models Good Prompt Optimizers?](https://mlsanity.com/paper/2402.02101/) (2024)
- [Efficient Prompt Optimization Through the Lens of Best Arm Identification](https://mlsanity.com/paper/2402.09723/) (2024)
- [Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars](https://mlsanity.com/paper/2405.16122/) (2024)
- [PromptWizard: Task-Aware Prompt Optimization Framework](https://mlsanity.com/paper/2405.18369/) (2024)
- [Prompt Optimization with Human Feedback](https://mlsanity.com/paper/2405.17346/) (2024)
- [CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks](https://mlsanity.com/paper/2507.23751/) (2025)
- [Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers](https://mlsanity.com/paper/2310.02905/) (2023)
- [Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization](https://mlsanity.com/paper/2406.15708/) (2024)
- [On Discrete Prompt Optimization for Diffusion Models](https://mlsanity.com/paper/2407.01606/) (2024)
- [Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism](https://mlsanity.com/paper/2403.02054/) (2024)
- [Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning](https://mlsanity.com/paper/2310.11053/) (2023)
- [Instance-adaptive Zero-shot Chain-of-Thought Prompting](https://mlsanity.com/paper/2409.20441/) (2024)
- [Localized Zeroth-Order Prompt Optimization](https://mlsanity.com/paper/2403.02993/) (2024)
- [FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch](https://mlsanity.com/paper/2406.04824/) (2024)
- [AlpaGasus: Training A Better Alpaca with Fewer Data](https://mlsanity.com/paper/2307.08701/) (2023)
- [One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts](https://mlsanity.com/paper/2407.00256/) (2024)
- [MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization](https://mlsanity.com/paper/2503.16874/) (2025)
- [Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models](https://mlsanity.com/paper/2310.03123/) (2023)
- [A Better LLM Evaluator for Text Generation: The Impact of Prompt Output Sequencing and Optimization](https://mlsanity.com/paper/2406.09972/) (2024)
- [PRSA: Prompt Stealing Attacks against Real-World Prompt Services](https://mlsanity.com/paper/2402.19200/) (2024)
- [Learning to Reason via Program Generation, Emulation, and Search](https://mlsanity.com/paper/2405.16337/) (2024)
- [Hyperband-based Bayesian Optimization for Black-box Prompt Selection](https://mlsanity.com/paper/2412.07820/) (2024)

## Abstract (arXiv)

Large language models~(LLMs) are instruction followers, but it can be challenging to find the best instruction for different situations, especially for black-box LLMs on which backpropagation is forbidden. Instead of directly optimizing the discrete instruction, we optimize a low-dimensional soft prompt applied to an open-source LLM to generate the instruction for the black-box LLM. On each iteration of the proposed method, which we call InstructZero, a soft prompt is converted into an instruction using the open-source LLM, which is then submitted to the black-box LLM for zero-shot evaluation, and the performance is sent to Bayesian optimization to produce new soft prompts improving the zero-shot performance. We evaluate InstructZero on different combinations of open-source LLMs and APIs including Vicuna and ChatGPT. Our results show that InstructZero outperforms SOTA auto-instruction methods across a variety of downstream tasks. Our code and data are publicly available at https://github.com/Lichang-Chen/InstructZero.