Self-Supervised Prompt Optimization

Papers with Code Trending Papers
self-supervised-learning prompt-optimization large-language-models evaluation-methods meta-gpt

Summary

This paper introduces Self-Supervised Prompt Optimization (SPO), a framework that optimizes prompts for LLMs without external references by using output comparisons, significantly reducing costs and data requirements.

Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and iterative experimentation. While existing prompt optimization methods aim to automate this process, they rely heavily on external references such as ground truth or by humans, limiting their applicability in real-world scenarios where such data is unavailable or costly to obtain. To address this, we propose Self-Supervised Prompt Optimization (SPO), a cost-efficient framework that discovers effective prompts for both closed and open-ended tasks without requiring external reference. Motivated by the observations that prompt quality manifests directly in LLM outputs and LLMs can effectively assess adherence to task requirements, we derive evaluation and optimization signals purely from output comparisons. Specifically, SPO selects superior prompts through pairwise output comparisons evaluated by an LLM evaluator, followed by an LLM optimizer that aligns outputs with task requirements. Extensive experiments demonstrate that SPO outperforms state-of-the-art prompt optimization methods, achieving comparable or superior results with significantly lower costs (e.g., 1.1% to 5.6% of existing methods) and fewer samples (e.g., three samples). The code is available at https://github.com/geekan/MetaGPT.
Original Article
View Cached Full Text

Cached at: 05/08/26, 08:59 AM

Paper page - Self-Supervised Prompt Optimization

Source: https://huggingface.co/papers/2502.06855

Abstract

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

Well-designed prompts are crucial for enhancing Large language models’ (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. However, manually designed prompts require expertise and iterative experimentation. While existingprompt optimizationmethods aim to automate this process, they rely heavily on external references such as ground truth or by humans, limiting their applicability in real-world scenarios where such data is unavailable or costly to obtain. To address this, we proposeSelf-Supervised Prompt Optimization (SPO), a cost-efficient framework that discovers effective prompts for both closed and open-ended tasks without requiring external reference. Motivated by the observations thatprompt qualitymanifests directly in LLM outputs andLLMscan effectively assess adherence to task requirements, we derive evaluation and optimization signals purely from output comparisons. Specifically, SPO selects superior prompts through pairwise output comparisons evaluated by anLLM evaluator, followed by anLLM optimizerthat aligns outputs with task requirements. Extensive experiments demonstrate that SPO outperforms state-of-the-artprompt optimizationmethods, achieving comparable or superior results with significantly lower costs (e.g., 1.1% to 5.6% of existing methods) and fewer samples (e.g., three samples). The code is available at https://github.com/geekan/MetaGPT.

View arXiv pageView PDFGitHub67.8kautoAdd to collection

Get this paper in your agent:

hf papers read 2502\.06855

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2502.06855 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2502.06855 in a dataset README.md to link it from this page.

Spaces citing this paper4

Collections including this paper16

Browse 16 collections that include this paper

Similar Articles

SePO: Self-Evolving Prompt Agent for System Prompt Optimization

arXiv cs.CL

SePO (Self-Evolving Prompt Optimization) proposes a self-referential prompt agent that optimizes both task agents' system prompts and its own system prompt through an evolutionary search, outperforming Manual-CoT, TextGrad, and MetaSPO across five benchmarks including AIME'25, ARC-AGI-1, and GPQA.

SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration

arXiv cs.CL

Introduces SPO, a stochastic search framework for automatic prompt optimization, with three strategies including SAGE, an agent-guided multi-agent pipeline. Evaluated on benchmarks and deployed on a mental-health chatbot, showing improvements in retention through continuous optimization.

Self-Supervised Skill Optimization

arXiv cs.CL

This paper introduces Self-Supervised Skill Optimization (SSO), a framework that learns and optimizes reusable agent skills from unlabeled task instances using LLM-judged pairwise comparisons, without requiring ground-truth labels or rewards. SSO outperforms existing ground-truth-free prompt optimizers and approaches ground-truth-based methods on closed-ended benchmarks.