Optimizing Soft Prompt Tuning via Structural Evolution

• URL: http://arxiv.org/abs/2602.16500v1
• Date: Wed, 18 Feb 2026 14:43:20 GMT
• Title: Optimizing Soft Prompt Tuning via Structural Evolution
• Authors: Zhenzhen Huang, Chaoning Zhang, Haoyu Bian, Songbo Zhang, Chi-lok Andy Tai, Jiaquan Zhang, Caiyan Qin, Jingjing Qu, Yalan Ye, Yang Yang, Heng Tao Shen,
• Abstract summary: We propose a soft prompt tuning optimization method based on topological morphological evolution.<n>Specifically, we employ persistent homology from topological data analysis to quantify the structural representations of soft prompts.<n>We construct a loss function for optimizing soft prompt tuning, termed Topological Soft Prompt Loss (TSLoss)
• Score: 44.99047637666981
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Soft prompt tuning leverages continuous embeddings to capture task-specific information in large pre-trained language models (LLMs), achieving competitive performance in few-shot settings. However, soft prompts rely on high-dimensional, implicit representations and lack explicit semantics and traceable training behaviors, which limits their interpretability. To address this limitation, we propose a soft prompt tuning optimization method based on topological morphological evolution. Specifically, we employ persistent homology from topological data analysis (TDA) to quantify the structural representations of soft prompts in continuous parameter space and their training process evolution. Quantitative analysis shows that topologically stable and compact soft prompts achieve better downstream performance. Based on this empirical observation, we construct a loss function for optimizing soft prompt tuning, termed Topological Soft Prompt Loss (TSLoss). TSLoss guides the model to learn structurally stable adaptations by quantifying inter-parameter connectivity and redundancy. Extensive experiments show that training with TSLoss accelerates convergence and improves tuning performance, providing an interpretable method to understand and optimize soft prompt tuning from structural and topological perspectives.

Related papers

• Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework [0.6435984242701042]
  We propose TL-GPSGNT to improve graph-based time series forecasting models.<n>We use information-theoretic and correlation-based criteria to extract structurally informative subgraphs.<n>We show that TL-GPSGNT consistently outperforms baselines in low-data transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-04T02:41:29Z)
• Renormalization Group Guided Tensor Network Structure Search [58.0378300612202]
  Network structure search (TN-SS) aims to automatically discover optimal network topologies and rank robustness for efficient tensor decomposition in high-dimensional data representation.<n>We propose RGTN (Renormalization Group guided Network search), a physics-inspired framework transforming TN-SS via multi-scale renormalization group flows.
  arXiv  Detail & Related papers  (2025-12-31T06:31:43Z)
• Tuning for Trustworthiness -- Balancing Performance and Explanation Consistency in Neural Network Optimization [49.567092222782435]
  We introduce the novel concept of XAI consistency, defined as the agreement among different feature attribution methods.<n>We create a multi-objective optimization framework that balances predictive performance with explanation.<n>Our research provides a foundation for future investigations into whether models from the trade-off zone-balancing performance loss and XAI consistency-exhibit greater robustness.
  arXiv  Detail & Related papers  (2025-05-12T13:19:14Z)
• Graph-Based Spectral Decomposition for Parameter Coordination in Language Model Fine-Tuning [5.69600290598441]
  The goal is to improve both fine-tuning efficiency and structural awareness during training.<n>A weighted graph is constructed, and Laplacian spectral decomposition is applied to enable frequency-domain modeling.<n>A spectral filtering mechanism is introduced during the optimization phase, enhancing the model's training stability and convergence behavior.
  arXiv  Detail & Related papers  (2025-04-28T08:42:35Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Contextual Subspace Manifold Projection for Structural Refinement of Large Language Model Representations [0.0]
  Internal representations within deep neural architectures encode high-dimensional abstractions of linguistic structures.<n>This paper introduces a structured refinement technique that selectively reconfigures token embeddings through controlled subspace constraints.<n> Empirical evaluations demonstrated that the structured intervention reduced anisotropy, leading to improved representation compactness.
  arXiv  Detail & Related papers  (2025-02-12T00:00:37Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer [94.23904400441957]
  We introduce perturbation-based regularizers, which can smooth the loss landscape, into prompt tuning. We design two kinds of perturbation-based regularizers, including random-noise-based and adversarial-based. Our new algorithms improve the state-of-the-art prompt tuning methods by 1.94% and 2.34% on SuperGLUE and FewGLUE benchmarks, respectively.
  arXiv  Detail & Related papers  (2023-05-03T20:30:51Z)
• Optimisation of Structured Neural Controller Based on Continuous-Time Policy Gradient [2.297079626504224]
  This study presents a policy optimisation framework for structured nonlinear control of continuous-time (deterministic) dynamic systems. The proposed approach prescribes a structure for the controller based on relevant scientific knowledge. Numerical experiments on aerospace applications illustrate the utility of the structured nonlinear controller optimisation framework.
  arXiv  Detail & Related papers  (2022-01-17T08:06:19Z)

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.