SAPO, a segment-level APO method that decomposes prompts into role, context, tasks, and output format, then applies targeted improvements based on top-5 and bottom-5 examples, achieves the best average score against Zero-shot and strong APO baselines.
Abstract
Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a segment-level APO method that decomposes prompts into role, context, tasks, and output format, then applies targeted improvements based on top-5 and bottom-5 examples. The optimization loop uses one LLM with static meta-prompts and structured outputs for segmentation, weakness analysis, and candidate generation. We describe a train/validation protocol and a two-stage generation process: (1) segment-level diagnosis and recommendation extraction, (2) candidate synthesis constrained by weak/strong segment signals. Using the evaluation setup across SQuADv2, TweetEval, XSUM, CommonGen, and GSM8K on GPT-3.5-Turbo and GPT-4o-mini, SAPO achieves the best average score against Zero-shot and strong APO baselines including APE, OPRO, EvoPrompt, GEPA, and StraGO.
ESO (Error-Structured Prompt Optimization), which decomposes prompt optimization into three phases: Diagnose clusters all training errors into structural patterns in one round; generate candidates via four complementary strategies with independent biases; Select applies bootstrap stability selection.
This paper introduces SEPO (Structural, Evidence-grounded Prompt Optimization), a multi-trajectory prompt optimiser centred on edit-effect lineage feedback that makes prompt optimisation addressable, attributable, and actionable.
Xiao-Yu Ma, Hao-Yue Liu, Yiwen Li et al.· 1 citation
It is shown that prompt engineering "ages" in a model-family-specific way: Newer GPT models exhibit diminishing or even negative marginal gains from structured prompting, suggesting that instruction-following and reasoning scaffolds are increasingly internalized, whereas Qwen models continue to benefit substantially fr...
A. Rudyk, Julian Oertel, Regina Hebig· 0 citations
DynaContext is introduced, a framework that combines an offline-optimized extraction core, learned with GEPA or SkillOpt, with inference-time contextual adaptation and validation-gated self-improvement, with inference-time contextual adaptation and validation-gated self-improvement.
Joe Yu, Shibin Thomas Stanley Paul, Sven Mayer· 0 citations
Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. Each program composes alpha-masked layers whose shared spatial expressions define coverage and physic...
This work investigates LLM-based evaluators of natural language generation quality mechanistically through an eight-attack perturbation taxonomy across the Readability and Adequacy dimensions of NLG quality, a generation pipeline that produces paired clean and corrupt summaries with controlled error intensity and expli...
Himil Vasava, Ming-Zhou Jiang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
