paper-with-me

Papers

Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs

2026-04-08 · Haoyue Liu, Zhichao Wang, Yongxin Guo, Haoran Shou, Xiaoying Tang arxiv

Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens. We propose Adaptive Prompt Structure Factorization (aPSF), an API-only framework (prompt-in/text-out; no access to model internals) that uses an Architect model to discover task-specific prompt structures as semantic factors. aPSF then performs interventional, single-factor updates: interventional factor-level scoring estimates each factor's marginal contribution via validation-performance changes, and error-guided factor selection routes updates to the current dominant failure source for more sample-efficient optimization. Across multiple advanced reasoning benchmarks, aPSF outperforms strong baselines including principle-aware optimizers, improving accuracy by up to +2.16 percentage points on average, and reduces optimization cost by 45--87% tokens on MultiArith while reaching peak validation in 1 step.

📄 PDF Abstract BibTeX arXiv:2604.06699

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Deep Self-representative Concept Factorization Network for Representation Learning

2019-12-13 · Yan Zhang, Zhao Zhang, Zheng Zhang, Mingbo Zhao 외

In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep fe…

ClusteringRepresentation Learning

Concept Factorization via Self-Representation and Adaptive Graph Structure Learning

2025-05-06 · Zhengqin Yang, Di wu, Jia Chen, Xin Luo

Concept Factorization (CF) models have attracted widespread attention due to their excellent performance in data clustering. In recent years, many variant models based on CF have achieved great success in clustering by t…

ClusteringGraph structure learning

Spatio-Temporal Tensor Sketching via Adaptive Sampling

2020-06-21 · Jing Ma, Qiuchen Zhang, Joyce C. Ho, Li Xiong

Mining massive spatio-temporal data can help a variety of real-world applications such as city capacity planning, event management, and social network analysis. The tensor representation can be used to capture the correl…

Management

Joint Label Prediction based Semi-Supervised Adaptive Concept Factorization for Robust Data Representation

2019-05-25 · Zhao Zhang, Yan Zhang, Guangcan Liu, Jinhui Tang 외

Constrained Concept Factorization (CCF) yields the enhanced representation ability over CF by incorporating label information as additional constraints, but it cannot classify and group unlabeled data appropriately. Mini…

Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Bias

2025-10-27 · Yuhan Yang, Xingbo Fu, Jundong Li arxiv

Self-supervised pre-training on unlabeled graph data has become a common paradigm for Graph Neural Networks (GNNs). However, an objective gap often remains between pre-training objectives and downstream tasks. To bridge …

Node Classification