Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

• URL: http://arxiv.org/abs/2509.24130v1
• Date: Sun, 28 Sep 2025 23:57:05 GMT
• Title: Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
• Authors: Guancheng Wan, Lucheng Fu, Haoxin Liu, Yiqiao Jin, Hui Yi Leong, Eric Hanchen Jiang, Hejia Geng, Jinhe Bi, Yunpu Ma, Xiangru Tang, B. Aditya Prakash, Yizhou Sun, Wei Wang,
• Abstract summary: We introduce TARE, a derivative-free framework that alternates between an inner, sampling-based adversarial search that stresses a prompt with hard paraphrases.<n>We also propose ATARE, which learns anisotropic weights to shape the semantic neighborhood and adapts its radius over time to balance exploration and fidelity.
• Score: 57.67972800581953
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The performance of Large Language Models (LLMs) hinges on carefully engineered prompts. However, prevailing prompt optimization methods, ranging from heuristic edits and reinforcement learning to evolutionary search, primarily target point-wise accuracy. They seldom enforce paraphrase invariance or searching stability, and therefore cannot remedy this brittleness in practice. Automated prompt search remains brittle: small, semantically preserving paraphrases often cause large performance swings. We identify this brittleness as the textual sharpness of the prompt landscape. In this work, we provide the first formal treatment of textual sharpness in the discrete, semantic space of prompts, together with an operational robustness criterion over a semantic neighborhood; the design is black-box or API-only, requiring no gradients to update the model's parameters. Then we introduce TARE (Textual Sharpness-Aware Evolving), a derivative-free framework that alternates between an inner, sampling-based adversarial search that stresses a prompt with hard paraphrases and an outer, robust selection that prefers candidates whose neighborhoods remain strong. We further propose ATARE, which learns anisotropic weights to shape the semantic neighborhood and adapts its radius over time to balance exploration and fidelity. Diverse tasks evaluate our methods, whose design for minimizing textual sharpness gap leads to prompts that preserve accuracy under paraphrasing, outperforming accuracy-only prompt search while remaining computationally practical.

Related papers

• Dual-Granularity Semantic Prompting for Language Guidance Infrared Small Target Detection [102.1314414263959]
  Infrared small target detection remains challenging due to limited feature representation and severe background interference.<n>We propose DGSPNet, an end-to-end language prompt-driven framework.<n>Our method significantly improves detection accuracy and achieves state-of-the-art performance on three benchmark datasets.
  arXiv  Detail & Related papers  (2025-11-24T16:58:23Z)
• Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient [50.15090865963094]
  We introduce PertBench, a comprehensive benchmark dataset that includes a wide range of input perturbations.<n>Our analysis reveals substantial vulnerabilities in existing prompt generation strategies.<n>We propose PGO, a gradient-free prompt generation framework that leverages perturbation types as pseudo-gradient signals.
  arXiv  Detail & Related papers  (2024-12-24T06:05:08Z)
• Eliciting Textual Descriptions from Representations of Continuous Prompts [11.489611613744724]
  We propose a new approach to interpret continuous prompts that elicits textual descriptions from their representations during model inference. We show our method often yields accurate task descriptions which become more faithful as task performance increases. InSPEcT can be leveraged to debug unwanted properties in continuous prompts and inform developers on ways to mitigate them.
  arXiv  Detail & Related papers  (2024-10-15T14:46:11Z)
• Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL [29.01858866450715]
  We present RLPrompt, which aims to find optimal prompt tokens leveraging soft Q-learning. While the results show promise, we have observed that the prompts frequently appear unnatural, which impedes their interpretability. We address this limitation by using sparse Tsallis entropy regularization, a principled approach to filtering out unlikely tokens from consideration.
  arXiv  Detail & Related papers  (2024-07-20T03:10:19Z)
• Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
  Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
  arXiv  Detail & Related papers  (2024-03-01T09:01:53Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• PROMPT WAYWARDNESS: The Curious Case of Discretized Interpretation of Continuous Prompts [99.03864962014431]
  Fine-tuning continuous prompts for target tasks has emerged as a compact alternative to full model fine-tuning. In practice, we observe a "wayward" behavior between the task solved by continuous prompts and their nearest neighbor.
  arXiv  Detail & Related papers  (2021-12-15T18:55:05Z)
• LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching [66.65398852962177]
  We develop a novel Dynamic Re-read Network (DRr-Net) for sentence semantic matching. We extend DRr-Net to Locally-Aware Dynamic Re-read Attention Net (LadRa-Net) Experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching.
  arXiv  Detail & Related papers  (2021-08-06T02:07:04Z)

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.