How are Prompts Different in Terms of Sensitivity?
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.
Code (1)
Tasks
In-Context LearningPrompt EngineeringSensitivitySimilar Papers 제목 키워드 기반
A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment
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+1Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?
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
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 LearningDpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation
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 SegmentationStructured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
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