paper-with-me

홈 › Papers

How are Prompts Different in Terms of Sensitivity?

2023-11-13 · Sheng Lu, Hendrik Schuff, Iryna Gurevych

In-context learning (ICL) has become one of the most popular learning paradigms. While there is a growing body of literature focusing on prompt engineering, there is a lack of systematic analysis comparing the effects of prompts across different models and tasks. To address this gap, we present a comprehensive prompt analysis based on the sensitivity of a function. Our analysis reveals that sensitivity is an unsupervised proxy for model performance, as it exhibits a strong negative correlation with accuracy. We use gradient-based saliency scores to empirically demonstrate how different prompts affect the relevance of input tokens to the output, resulting in different levels of sensitivity. Furthermore, we introduce sensitivity-aware decoding which incorporates sensitivity estimation as a penalty term in the standard greedy decoding. We show that this approach is particularly helpful when information in the input is scarce. Our work provides a fresh perspective on the analysis of prompts, and contributes to a better understanding of the mechanism of ICL.

📄 PDF Abstract BibTeX arXiv:2311.07230

Code (1)

ukplab/naacl2024-prompt-sensitivity 공식 구현 pytorch

Tasks

In-Context LearningPrompt EngineeringSensitivity

Similar Papers 제목 키워드 기반

A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment

2025-04-16 · Negar Arabzadeh, Charles L. A . Clarke

Large Language Models (LLMs) are increasingly used to automate relevance judgments for information retrieval (IR) tasks, often demonstrating agreement with human labels that approaches inter-human agreement. To assess th…

Information RetrievalRAGRetrievalRetrieval-augmented Generation+1

Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?

2026-05-28 · Pawel Batorski, Abtin Pourhadi, Jerzy Sarosiek, Przemyslaw Spurek 외 arxiv

Large language models are highly sensitive to prompts, but this sensitivity is usually studied through task-relevant instructions, demonstrations, or reasoning cues. In this paper, we study a different form of prompt sen…

Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions

2026-08-19 · Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei 외 arxiv

The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic fluctuations in performance, a phenomen…

Few-Shot Learning

DpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation

2025-07-08 · Xinglong Liang, Jiaju Huang, Luyi Han, Tianyu Zhang 외 arxiv

PET-CT lesion segmentation is challenging due to noise sensitivity, small and variable lesion morphology, and interference from physiological high-metabolic signals. Current mainstream approaches follow the practice of o…

Lesion Segmentation

Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space

2026-02-27 · Jiasen Zheng, Zijun Zhou, Huajun Zhang, Junjiang Lin 외 arxiv

This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured promp…

Few-Shot Text Classification