# ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

arXiv: https://arxiv.org/abs/2410.12405 · HTML: https://mlsanity.com/paper/2410.12405/

## Key facts

- Cited by 149 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [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)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)

## Built on by (most cited first, 30 of 149)

- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [Are Your LLMs Capable of Stable Reasoning?](https://mlsanity.com/paper/2412.13147/) (2024)
- [DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation](https://mlsanity.com/paper/2503.01622/) (2025)
- [Brittlebench: Quantifying LLM robustness via prompt sensitivity](https://mlsanity.com/paper/2603.13285/) (2026)
- [Challenging the Evaluator: LLM Sycophancy Under User Rebuttal](https://mlsanity.com/paper/2509.16533/) (2025)
- [On Randomness in Agentic Evals](https://mlsanity.com/paper/2602.07150/) (2026)
- [Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization](https://mlsanity.com/paper/2502.04295/) (2025)
- [Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles](https://mlsanity.com/paper/2507.22168/) (2025)
- [Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective](https://mlsanity.com/paper/2504.03255/) (2025)
- [Promptception: How Sensitive Are Large Multimodal Models to Prompts?](https://mlsanity.com/paper/2509.03986/) (2025)
- [Triangulating LLM Progress through Benchmarks, Games, and Cognitive Tests](https://mlsanity.com/paper/2502.14359/) (2025)
- [ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments](https://mlsanity.com/paper/2505.22169/) (2025)
- [Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure](https://mlsanity.com/paper/2604.02547/) (2026)
- [Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data](https://mlsanity.com/paper/2503.05587/) (2025)
- [When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs](https://mlsanity.com/paper/2508.11383/) (2025)
- [Culture is Everywhere: A Call for Intentionally Cultural Evaluation](https://mlsanity.com/paper/2509.01301/) (2025)
- [Silenced Biases: The Dark Side LLMs Learned to Refuse](https://mlsanity.com/paper/2511.03369/) (2025)
- [JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems](https://mlsanity.com/paper/2604.23478/) (2026)
- [Exploring the Potential for Large Language Models to Demonstrate Rational Probabilistic Beliefs](https://mlsanity.com/paper/2504.13644/) (2025)
- [PRL: Prompts from Reinforcement Learning](https://mlsanity.com/paper/2505.14412/) (2025)
- [Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs](https://mlsanity.com/paper/2508.19432/) (2025)
- [Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems](https://mlsanity.com/paper/2603.00131/) (2026)
- [Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing](https://mlsanity.com/paper/2505.21701/) (2025)
- [CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments](https://mlsanity.com/paper/2509.13588/) (2025)
- [Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning](https://mlsanity.com/paper/2510.01032/) (2025)
- [The Fragility Of Moral Judgment In Large Language Models](https://mlsanity.com/paper/2603.05651/) (2026)
- [Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models](https://mlsanity.com/paper/2509.03036/) (2025)
- [Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation](https://mlsanity.com/paper/2506.17442/) (2025)
- [ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models](https://mlsanity.com/paper/2601.15812/) (2026)
- [Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction](https://mlsanity.com/paper/2502.16280/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but their performance is highly sensitive to the prompts utilized. This variability poses challenges for accurate assessment and user satisfaction. Current research frequently overlooks instance-level prompt variations and their implications on subjective evaluations. To address these shortcomings, we introduce ProSA, a framework designed to evaluate and comprehend prompt sensitivity in LLMs. ProSA incorporates a novel sensitivity metric, PromptSensiScore, and leverages decoding confidence to elucidate underlying mechanisms. Our extensive study, spanning multiple tasks, uncovers that prompt sensitivity fluctuates across datasets and models, with larger models exhibiting enhanced robustness. We observe that few-shot examples can alleviate this sensitivity issue, and subjective evaluations are also susceptible to prompt sensitivities, particularly in complex, reasoning-oriented tasks. Furthermore, our findings indicate that higher model confidence correlates with increased prompt robustness. We believe this work will serve as a helpful tool in studying prompt sensitivity of LLMs. The project is released at: https://github.com/open-compass/ProSA .