# Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization

arXiv: https://arxiv.org/abs/2406.15708 · HTML: https://mlsanity.com/paper/2406.15708/

## Key facts

- Cited by 28 papers in the map (data through 7 Oct 2026).
- Builds on 43 of its 62 references that are in the map.
- First posted on arXiv 22 Jun 2024.

## Builds on (most cited first, 30 of 43)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [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)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [What Makes Good Examples for Visual In-Context Learning?](https://mlsanity.com/paper/2301.13670/) (2023)
- [Compositional Exemplars for In-context Learning](https://mlsanity.com/paper/2302.05698/) (2023)
- [Large Language Models as Evolutionary Optimizers](https://mlsanity.com/paper/2310.19046/) (2023)
- [Gecko: Versatile Text Embeddings Distilled from Large Language Models](https://mlsanity.com/paper/2403.20327/) (2024)
- [On the Relation between Sensitivity and Accuracy in In-context Learning](https://mlsanity.com/paper/2209.07661/) (2022)

## Built on by (most cited first, 28 of 28)

- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [SPRIG: Improving Large Language Model Performance by System Prompt Optimization](https://mlsanity.com/paper/2410.14826/) (2024)
- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [Towards LLMs Robustness to Changes in Prompt Format Styles](https://mlsanity.com/paper/2504.06969/) (2025)
- [From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation](https://mlsanity.com/paper/2502.00330/) (2025)
- [Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent](https://mlsanity.com/paper/2502.11267/) (2025)
- [Hyperband-based Bayesian Optimization for Black-box Prompt Selection](https://mlsanity.com/paper/2412.07820/) (2024)
- [A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluation](https://mlsanity.com/paper/2412.15298/) (2024)
- [Meta-Prompt Optimization for LLM-Based Sequential Decision Making](https://mlsanity.com/paper/2502.00728/) (2025)
- [A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm](https://mlsanity.com/paper/2502.18746/) (2025)
- [CAPO: Cost-Aware Prompt Optimization](https://mlsanity.com/paper/2504.16005/) (2025)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [Scaling Textual Gradients via Sampling-Based Momentum](https://mlsanity.com/paper/2506.00400/) (2025)
- [Code-enabled language models can outperform reasoning models on diverse tasks](https://mlsanity.com/paper/2510.20909/) (2025)
- [Towards Compute-Optimal Many-Shot In-Context Learning](https://mlsanity.com/paper/2507.16217/) (2025)
- [Agentic Policy Optimization via Instruction-Policy Co-Evolution](https://mlsanity.com/paper/2512.01945/) (2025)
- [TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization](https://mlsanity.com/paper/2605.21318/) (2026)
- [Towards more Contextual Agents: An extractor-Generator Optimization Framework](https://mlsanity.com/paper/2502.12926/) (2025)
- [Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language Models](https://mlsanity.com/paper/2503.23503/) (2025)
- [MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs](https://mlsanity.com/paper/2601.18113/) (2026)
- [CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution](https://mlsanity.com/paper/2605.13295/) (2026)
- [FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast](https://mlsanity.com/paper/2605.16233/) (2026)
- [Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing](https://mlsanity.com/paper/2507.08109/) (2025)
- [DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization](https://mlsanity.com/paper/2510.18257/) (2025)
- [APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection](https://mlsanity.com/paper/2606.11459/) (2026)
- [SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration](https://mlsanity.com/paper/2606.18902/) (2026)
- [Towards Spec Learning: Inference-Time Alignment from Preference Pairs](https://mlsanity.com/paper/2606.24004/) (2026)
- [Large language models in medical time series analysis](https://mlsanity.com/paper/2609.22262/) (2026)

## Abstract (arXiv)

Large language models have demonstrated remarkable capabilities, but their performance is heavily reliant on effective prompt engineering. Automatic prompt optimization (APO) methods are designed to automate this and can be broadly categorized into those targeting instructions (instruction optimization, IO) vs. those targeting exemplars (exemplar optimization, EO). Despite their shared objective, these have evolved rather independently, with IO receiving more research attention recently. This paper seeks to bridge this gap by comprehensively comparing the performance of representative IO and EO techniques both isolation and combination on a diverse set of challenging tasks. Our findings reveal that intelligently reusing model-generated input-output pairs obtained from evaluating prompts on the validation set as exemplars, consistently improves performance on top of IO methods but is currently under-investigated. We also find that despite the recent focus on IO, how we select exemplars can outweigh how we optimize instructions, with EO strategies as simple as random search outperforming state-of-the-art IO methods with seed instructions without any optimization. Moreover, we observe a synergy between EO and IO, with optimal combinations surpassing the individual contributions. We conclude that studying exemplar optimization both as a standalone method and its optimal combination with instruction optimization remain a crucial aspect of APO and deserve greater consideration in future research, even in the era of highly capable instruction-following models.