Boosting Self-Efficacy and Performance of Large Language Models via Verbal Efficacy Stimulations

TL;DR

This paper introduces Verbal Efficacy Stimulations (VES), a novel prompt technique inspired by social cognitive theory, to enhance the performance and self-efficacy of large language models across various tasks and difficulties.

Contribution

It proposes and evaluates three types of verbal prompts (encouraging, provocative, critical) to improve LLM performance, exploring their effects across different task difficulties and model types.

Findings

All three VES types generally improve LLM performance.

The most effective VES varies depending on the model and task difficulty.

Results align with psychological theories on self-efficacy and emotional influence.

Abstract

Significant improvements have been observed in the zero-shot capabilities of the Large Language Models (LLMs). Due to their high sensitivity to input, research has increasingly focused on enhancing LLMs' performance via direct and simple prompt engineering rather than intricate domain adaptation. Studies suggest that LLMs exhibit emotional intelligence, and both positive and negative emotions can potentially enhance task performances. However, prior interaction prompts have predominantly concentrated on a single stimulus type, neglecting to compare different stimulus effects, examine the influence of varying task difficulties, or explore underlying mechanisms. This paper, inspired by the positive correlation between self-efficacy and task performance within the social cognitive theory, introduces Verbal Efficacy Stimulations (VES). Our VES comprises three types of verbal prompts: encouraging, provocative, and critical, addressing six aspects such as helpfulness and competence. And we further categorize task difficulty, aiming to extensively investigate how distinct VES influence the self-efficacy and task achievements of language models at varied levels of difficulty. The experimental results show that the three types of VES improve the performance of LLMs on most tasks, and the most effective VES varies for different models. In extensive experiments, we have obtained some findings consistent with psychological theories, providing novel insights for future research.