4.pdf- “Understanding the Robustness of Large Language Models: PromptBench Analysis” – “Unveiling the Vulnerabilities of Large Language Models to Adversarial Prompts” – “Crafting More Robust Prompts: Insights from PromptBench Analysis” – “Examining the Transferability of Adversarial Prompts in Large Language Models” – “Enhancing Prompt Robustness: Practical Recommendations from PromptBench Study”

– Pre-trained language models (PLMs) have revolutionized NLP tasks.
– PLMs can be vulnerable to backdoor attacks, compromising their behavior.
– Existing backdoor removal methods rely on trigger inversion and fine-tuning.
– PromptFix proposes a novel backdoor mitigation strategy using adversarial prompt tuning.
– PromptFix uses soft tokens to approximate and counteract the trigger.
– It eliminates the need for enumerating possible backdoor configurations.
– PromptFix preserves model performance and reduces backdoor attack success rate.

– Solo Performance Prompting (SPP) enhances problem-solving abilities in complex tasks.
– SPP reduces factual hallucination and maintains strong reasoning capabilities.
– Cognitive synergy emerges in GPT-4 but not in less capable models.

– PromptBench is a benchmark to measure the robustness of Large Language Models (LLMs) to adversarial prompts.
– LLMs are not robust to adversarial prompts.
– The study includes diverse tasks and generates 4,788 adversarial prompts.
– Comprehensive analysis and recommendations are provided for prompt composition.
– Code and evaluation benchmark are available to the public.

– Solo Performance Prompting (SPP) helps a computer program think like different people.
– It uses different personas to solve problems and get accurate knowledge.
– SPP reduces mistakes and makes better plans compared to other methods.
– It works well in tasks like writing stories and solving puzzles.
– SPP is better in GPT-4 model compared to other models.