NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli

TL;DR

This paper introduces NegativePrompt, a psychological approach using negative emotional stimuli to significantly improve large language models' performance across various tasks, revealing new insights into emotion-driven AI enhancement.

Contribution

The paper presents a novel negative emotional stimuli method, NegativePrompt, demonstrating its effectiveness in enhancing LLM performance and providing insights into emotion and AI interaction.

Findings

NegativePrompt improves LLM performance by up to 46.25%

Significant performance gains across multiple LLMs and tasks

Attention visualization reveals mechanisms of emotional influence

Abstract

Large Language Models (LLMs) have become integral to a wide spectrum of applications, ranging from traditional computing tasks to advanced artificial intelligence (AI) applications. This widespread adoption has spurred extensive research into LLMs across various disciplines, including the social sciences. Notably, studies have revealed that LLMs possess emotional intelligence, which can be further developed through positive emotional stimuli. This discovery raises an intriguing question: can negative emotions similarly influence LLMs, potentially enhancing their performance? In response to this question, we introduce NegativePrompt, a novel approach underpinned by psychological principles, involving ten specifically designed negative emotional stimuli. We embark on rigorous experimental evaluations of five LLMs including Flan-T5-Large, Vicuna, Llama 2, ChatGPT, and GPT-4, across a set of 45 tasks. The results are revealing: NegativePrompt markedly enhances the performance of LLMs, evidenced by relative improvements of 12.89% in Instruction Induction tasks and 46.25% in BIG-Bench tasks. Moreover, we conduct attention visualization experiments to decipher the underlying mechanisms of NegativePrompt's influence. Our research contributes significantly to the understanding of LLMs and emotion interaction, demonstrating the practical efficacy of NegativePrompt as an emotion-driven method and offering novel insights for the enhancement of LLMs in real-world applications. The code is available at https://github.com/wangxu0820/NegativePrompt.