# How are Prompts Different in Terms of Sensitivity?

arXiv: https://arxiv.org/abs/2311.07230 · HTML: https://mlsanity.com/paper/2311.07230/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 60 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 30 of 48)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Trained Transformers Learn Linear Models In-Context](https://mlsanity.com/paper/2306.09927/) (2023)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective](https://mlsanity.com/paper/2305.15408/) (2023)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Transformers as Algorithms: Generalization and Stability in In-context Learning](https://mlsanity.com/paper/2301.07067/) (2023)

## Built on by (most cited first, 30 of 35)

- [POSIX: A Prompt Sensitivity Index For Large Language Models](https://mlsanity.com/paper/2410.02185/) (2024)
- [Do LLMs "know" internally when they follow instructions?](https://mlsanity.com/paper/2410.14516/) (2024)
- [Finding Visual Task Vectors](https://mlsanity.com/paper/2404.05729/) (2024)
- [Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning](https://mlsanity.com/paper/2406.10099/) (2024)
- [Paraphrase Types Elicit Prompt Engineering Capabilities](https://mlsanity.com/paper/2406.19898/) (2024)
- [A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment](https://mlsanity.com/paper/2504.12408/) (2025)
- [Small Languages, Big Models: A Study of Continual Training on Languages of Norway](https://mlsanity.com/paper/2412.06484/) (2024)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric](https://mlsanity.com/paper/2409.03735/) (2024)
- [Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages](https://mlsanity.com/paper/2411.02398/) (2024)
- [Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair](https://mlsanity.com/paper/2510.03217/) (2025)
- [Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More](https://mlsanity.com/paper/2503.10542/) (2025)
- [FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking](https://mlsanity.com/paper/2504.16188/) (2025)
- [E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models](https://mlsanity.com/paper/2406.10950/) (2024)
- [Benchmarking Abstractive Summarisation: A Dataset of Human-authored Summaries of Norwegian News Articles](https://mlsanity.com/paper/2501.07718/) (2025)
- [Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting](https://mlsanity.com/paper/2408.09365/) (2024)
- [RCScore: Quantifying Response Consistency in Large Language Models](https://mlsanity.com/paper/2510.26193/) (2025)
- [PLR: Plackett-Luce for Reordering In-Context Learning Examples](https://mlsanity.com/paper/2603.21373/) (2026)
- [Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries](https://mlsanity.com/paper/2606.09005/) (2026)
- [LLMs as Function Approximators: Terminology, Taxonomy, and Questions for Evaluation](https://mlsanity.com/paper/2407.13744/) (2024)
- [Information Anxiety in Large Language Models](https://mlsanity.com/paper/2411.10813/) (2024)
- [SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation](https://mlsanity.com/paper/2502.07101/) (2025)
- [Towards Contamination Resistant Benchmarks](https://mlsanity.com/paper/2505.08389/) (2025)
- [Improving Document Retrieval Coherence for Semantically Equivalent Queries](https://mlsanity.com/paper/2508.07975/) (2025)
- [DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation](https://mlsanity.com/paper/2512.22629/) (2025)
- [Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives](https://mlsanity.com/paper/2603.09994/) (2026)
- [Prompts Without Evidence: How Neuroimaging Mentions Shift Clinical Vision-Language Model Predictions](https://mlsanity.com/paper/2603.28387/) (2026)
- [Prompt-Driven Code Summarization: A Systematic Literature Review](https://mlsanity.com/paper/2604.15385/) (2026)
- [From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media](https://mlsanity.com/paper/2604.21786/) (2026)
- [Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?](https://mlsanity.com/paper/2605.29678/) (2026)

## Abstract (arXiv)

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.