PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptRobust, a robustness benchmark designed to measure LLMs' resilience to adversarial prompts. This study uses a plethora of adversarial textual attacks targeting prompts across multiple levels: character, word, sentence, and semantic. The adversarial prompts, crafted to mimic plausible user errors like typos or synonyms, aim to evaluate how slight deviations can affect LLM outcomes while maintaining semantic integrity. These prompts are then employed in diverse tasks including sentiment analysis, natural language inference, reading comprehension, machine translation, and math problem-solving. Our study generates 4,788 adversarial prompts, meticulously evaluated over 8 tasks and 13 datasets. Our findings demonstrate that contemporary LLMs are not robust to adversarial prompts. Furthermore, we present a comprehensive analysis to understand the mystery behind prompt robustness and its transferability. We then offer insightful robustness analysis and pragmatic recommendations for prompt composition, beneficial to both researchers and everyday users.
Code (1)
Tasks
Cross-Lingual Paraphrase IdentificationMachine TranslationMathNatural Language InferenceReading ComprehensionSentenceSentiment AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
Prompt-based adversarial attacks have become an effective means to assess the robustness of large language models (LLMs). However, existing approaches often treat prompts as monolithic text, overlooking their structural …
Adversarial RobustnessEvaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of co…
SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts
Traditional methods for evaluating the robustness of large language models (LLMs) often rely on standardized benchmarks, which can escalate costs and limit evaluations across varied domains. This paper introduces a novel…
DescriptiveKnowledge GraphsOn Evaluating Adversarial Robustness of Large Vision-Language Models
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models…
Adversarial Robustnessmultimodal generationResponse GenerationRevisiting DeepFool: generalization and improvement
Deep neural networks have been known to be vulnerable to adversarial examples, which are inputs that are modified slightly to fool the network into making incorrect predictions. This has led to a significant amount of re…
Adversarial AttackAdversarial RobustnessComputational Efficiency