Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Deep Self-representative Concept Factorization Network for Representation Learning
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 LearningConcept Factorization via Self-Representation and Adaptive Graph Structure Learning
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 learningSpatio-Temporal Tensor Sketching via Adaptive Sampling
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…
ManagementJoint Label Prediction based Semi-Supervised Adaptive Concept Factorization for Robust Data Representation
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
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