$p1$: Better Prompt Optimization with Fewer Prompts

• URL: http://arxiv.org/abs/2604.08801v1
• Date: Thu, 09 Apr 2026 22:31:15 GMT
• Title: $p1$: Better Prompt Optimization with Fewer Prompts
• Abstract summary: We show that prompt optimization succeeds when variance among system prompts is large, but fails when variance among responses dominates the variance of the system prompts.<n>We propose $p1$, a simple user prompt filtering method that selects a small subset of user prompts with high variance across candidate system prompts.
• Score: 49.20082664169319
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt optimization improves language models without updating their weights by searching for a better system prompt, but its effectiveness varies widely across tasks. We study what makes a task amenable to prompt optimization. We show that the reward variance across different system prompts can be decomposed into two components: variance among responses, which captures generation stochasticity, and variance among system prompts, which captures differences in system prompt quality. Prompt optimization succeeds when variance among system prompts is sufficiently large, but fails when variance among responses dominates the variance of the system prompts. Surprisingly, we further show that scaling to more user prompts can hurt optimization by reducing variance among system prompts, especially on heterogeneous datasets where different user prompts favor different system prompts. Motivated by this insight, we propose $p1$, a simple user prompt filtering method that selects a small subset of user prompts with high variance across candidate system prompts. This subset of user prompts allows one to distinguish a good system prompt from a bad one, making system optimization easier. Experiments on reasoning benchmarks show that $p1$ substantially improves prompt optimization over training on the full dataset and outperforms strong baselines such as GEPA. Notably, training on only two prompts from AIME 24 yields a system prompt that generalizes well to other reasoning benchmarks.

Related papers

• Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO [14.116598550478722]
  System prompts are widely employed to steer response behavior, but they are typically optimized for average-case quality.<n>We formulate a constrained mixed-strategy GroupDRO framework for system-prompt selection.<n>Our framework assigns weights to system prompts in an existing pool to minimize the worst-case information-quality loss.
  arXiv  Detail & Related papers  (2026-08-05T01:35:08Z)
• MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs [5.054661352089593]
  Biased or harmful concepts, e.g. gender or bio-weapons, can lead to unsafe or unethical responses for many such prompts.<n>We show that fine-tuning using the worst prompt type'' for concept prediction (with the highest concept accuracy) improves the average unlearning performance.<n>Our proposed method, MPSelectTune, is a two-stage approach that minimizes the concept accuracy of the highest accuracy-prompt type, after fine-tuning using a novel multi-task loss.
  arXiv  Detail & Related papers  (2026-07-04T15:52:16Z)
• GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer [51.31263673158136]
  GFlowPO casts prompt search as a posterior inference problem over latent prompts regularized by a meta-prompted reference-LM prior.<n>GFlowPO consistently outperforms recent discrete prompt optimization baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:30:03Z)
• System Prompt Optimization with Meta-Learning [64.74765550805024]
  We introduce the novel problem of bilevel system prompt optimization, whose objective is to design system prompts that are robust to diverse user prompts.<n>We propose a meta-learning framework, which meta-learns the system prompt by optimizing it over various user prompts across multiple datasets.<n>We conduct experiments on 14 unseen datasets spanning 5 different domains, on which we show that our approach produces system prompts that generalize effectively to diverse user prompts.
  arXiv  Detail & Related papers  (2025-05-14T16:46:15Z)
• Has My System Prompt Been Used? Large Language Model Prompt Membership Inference [56.20586932251531]
  We develop Prompt Detective, a statistical method to reliably determine whether a given system prompt was used by a third-party language model.<n>Our work reveals that even minor changes in system prompts manifest in distinct response distributions, enabling us to verify prompt usage with statistical significance.
  arXiv  Detail & Related papers  (2025-02-14T08:00:42Z)
• SPRIG: Improving Large Language Model Performance by System Prompt Optimization [45.96513122345295]
  Large Language Models (LLMs) have shown impressive capabilities in many scenarios, but their performance depends on the choice of prompt. We propose SPRIG, an edit-based genetic algorithm that iteratively constructs prompts from prespecified components to maximize the model's performance in general scenarios. We evaluate the performance of system prompts on a collection of 47 different types of tasks to ensure generalizability.
  arXiv  Detail & Related papers  (2024-10-18T18:51:44Z)
• Demystifying Prompts in Language Models via Perplexity Estimation [109.59105230163041]
  Performance of a prompt is coupled with the extent to which the model is familiar with the language it contains. We show that the lower the perplexity of the prompt is, the better the prompt is able to perform the task.
  arXiv  Detail & Related papers  (2022-12-08T02:21:47Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.