Boosting Self-Efficacy and Performance of Large Language Models via Verbal Efficacy Stimulations
This research addresses the problem of optimizing Large Language Models' performance for natural language processing tasks, which is significant for the AI research community, particularly those working on language models, and presents an incremental approach to enhancing their capabilities.
This study tackled the problem of improving Large Language Models' performance and found that Verbal Efficacy Stimulations can enhance their self-efficacy and task achievements, with varying effectiveness across different models and task difficulties. The experimental results showed improvements in performance, although specific numbers are not provided.
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.