Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
This addresses a critical issue for LLM users in enhancing robustness in reasoning tasks, though it is incremental as it builds on existing prompting methods.
The paper tackles the problem that role-playing prompts can degrade LLM reasoning capabilities in zero-shot tasks, and proposes the Jekyll & Hyde framework to mitigate this by ensembling role-playing and neutral prompts, improving reasoning on 12 datasets.
Recent studies demonstrate that prompting a role-playing persona to an LLM improves reasoning capability. However, assigning an adequate persona is difficult since LLMs are extremely sensitive to assigned prompts; thus, inaccurately defined personas sometimes hinder LLMs and degrade their reasoning capabilities. In this paper, we first investigate the potential negative impact of injecting persona into language models. Furthermore, we propose a novel framework, Jekyll \& Hyde, which ensembles the outcomes of both role-playing and neutral prompts to enhance the robustness of reasoning ability. Specifically, Jekyll \& Hyde predicts an appropriate persona using an LLM when defining the role-playing prompt. Then, Jekyll \& Hyde collects two potential solutions from role-playing and neutral prompts and selects a better solution using the LLM evaluator. The experimental analysis demonstrates that role-playing prompts sometimes distract LLMs, degrading their reasoning abilities in 7 out of 12 datasets in llama3. Meanwhile, Jekyll \& Hyde improve reasoning capabilities by selecting better choices among the potential solutions on twelve widely-used natural language reasoning datasets. In addition, we reveal that assigning LLM-generated personas obtains more stable results than handcrafted personas.