🟢 Role Prompting

Last updated on August 27, 2024 by Valeriia Kuka

We've already covered role prompting in the basic section of this guide. If you want you can start there. Now, we'll dive into a more advanced discussion.

What is Role Prompting?

If you’re interested in prompting, you’ve probably already come across this technique many times when finding prompt templates for different applications. Most of them start with: “I want you to act as …” or “You’re a …”

This act of assigning a role to a model you’re prompting is called role prompting¹² or role-play prompting³ or persona prompting⁴⁵. Here is an example of using role prompting:

In this prompt, the role is "historian". Other examples of roles include occupational roles like “plumber,” “therapist” or interpersonal “friend,” “mother,” or “supervisor”. You can find other examples of roles in the table¹ below:

Category	Examples
Family	mother (mom, mum, mommy), father (dad, papa, daddy), son, daughter, etc.
School	student, professor, tutor, instructor, etc.
Romantic	partner, husband, wife, etc.
Work	coworker, supervisor, colleague, boss
Social	friend, best friend, stranger, buddy, etc.
AI	AI language model, Policy Analysis AI, Medical Diagnostic AI, etc.
Occupations	driver, accountant, banker, dentist, etc.

How to Use Role Prompting?

One obvious use case for role prompting is text styling and imitation⁶. Interestingly, recent studies¹³ have shown that role prompting can also enhance the performance of prompted models in tasks such as reasoning.

In the following sections, we'll demonstrate how to leverage role prompting for each of these goals.

Style Imitation

Here, we make the AI imitate the writing style of a person.

This can be used to change the tone, style, and even the depth of the information presented.

Email Drafting

Imagine you need to write an outreach email to a potential marketing partner, and it's your first time doing it.

You go to your favorite LLM for help. Here's what you'll get if you write a simple prompt:

Compare this to the result you could get with role prompting:

You can make your communication more business-like and action-driven. This can help the person on the other end see that you get them and can speak their language. You can even customize your prompt based on the recipient's occupation or the individual most competent for the task.

Concept Explanation

Picture another example. Your boss mentioned a new concept for you, API. And you don't have the time to read through explanatory articles. So you ask an LLM.

Sounds good, but can be hard to understand as there are still some unknown concepts like "features of a program" and "program" itself. Let's try role prompting:

Looks more comprehensive and digestible. Now the LLM also included an analogy with a menu in a restaurant which is very helpful to grasp the key idea of the API.

Researchers also tried out framing prompts as a teacher-student dialogue instead of just telling an LLM to be thorough and simple⁶. They found that this approach leads to more stable and consistent outputs from the model.

Writing an Entertaining Story

Your toddler likes to read Joanne Rowling and have already read all the bibliography. You can ask to an LLM imitate Joanne Rowling's style and write a short story. Here's the prompt you can try yourself to compare results.

Simple prompt:

Role prompt:

Enhanced LLM Accuracy

Role prompting can be used to improve accuracy on certain problems, like general world knowledge¹ and reasoning³. While this statement is backed by some research, this area has not been studied enough, as we discussed in our article⁷.

Here are a few recommendations for creating role prompts that improve accuracy:

• Use non-intimate interpersonal roles: Non-intimate interpersonal roles yield better results than occupational roles, especially in settings such as schools, social environments, and workplaces.
• Use gender-neutral roles: Gender-neutral terms in prompts generally lead to better performance. Prompts with male roles often outperform those with female roles.
• Use audience or role prompt, don’t use interpersonal prompts:
  • Do: Audience prompt – You are talking to a/an [role]
  • Do: Role prompt – You are a/an [role]
  • Don’t: Interpersonal prompt – You are talking to your [role]
  • Don’t use imaginative constructs: Directly specifying the role or audience is more effective than prompting the model to "Imagine" the role
• Use a two-staged approach³:
  • First, assign a role to the model and add details of this role. Let the LLM write an output.
  • Second, write your question or task for the LLM.

We summarize these best practices in one example with an employee-boss setting and a task to craft an elevator pitch.

Step 1:

Step 2:

Expressing Complex Ideas and Subtle Behaviors

Invoking figures such as Mahatma Gandhi, Ayn Rand, or Eliezer Yudkowksy can subtly imply specific moral criteria without explicitly stating them⁶. This could have different applications, here are some of them:

• Educational chatbots offering advice based on the beliefs of figures like Gandhi, guiding students to explore various ethical perspectives.
• Chatbots engaging students in discussions that align with specific philosophical ideologies, helping them deepen their understanding of complex moral frameworks.
• As an opinion writer, you could frame your arguments by invoking principles associated with specific figures.

Limitations of Role Prompting

How well role prompting works depends on how each role is encoded and represented in the LLM. If the role isn’t well-represented or is misrepresented in the training data, the model might respond inaccurately or inappropriately when prompted with that role.

Another limitation is in the data LLMs are trained on. Since LLMs learn from big datasets that can have biases, role prompting could accidentally reinforce stereotypes or biased behaviors. For example, if a role is often linked to certain traits or behaviors in the training data, the model might repeat those connections, even if they’re wrong or inappropriate.

The research that guides our best practices is limited by the number of roles checked and the specific models used. Keep this in mind as you continue, and be cautious of potential biases or misrepresentations when applying role prompting in your work.

Conclusion

Role prompting is a powerful technique that guides LLM's behavior by assigning it specific roles, enhancing the style, accuracy, and depth of its outputs. Whether you're aiming for a certain tone, improving clarity, or eliciting complex and nuanced responses, role prompting can be of help. By adhering to best practices and being aware of potential pitfalls, you can fully leverage role prompting, making your interactions with language models more effective and tailored to your specific needs.

Further Reading

This section highlights some of the latest research papers on role prompting, which propose more sophisticated systems in this area. Each paper warrants a separate review, but if you’re interested, feel free to dive into the further reading.

• "Evaluating Persona Prompting for Question Answering Tasks"⁸ proposes different strategies for composing prompts with role prompting and investigates how different persona styles influence the performance of LLMs, particularly in handling questions with varying levels of "openness." This "openness" refers to the number of correct answers and the various ways those answers can be expressed. The paper also proposes methods for auto-generating roles and introduces a roundtable setting where several agents each take on one role.

• "Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation"⁹ proposes a general prompt structure for role prompting consisting of system instructions, situational context, response instructions, and conversation history, which can be tailored to different conversational tasks. The method allows LLMs to adopt roles that enhance their conversational abilities, such as empathy and engagement, effectively improving open-domain conversations in various languages, especially in French.

• "Large Language Models are Diverse Role-Players for Summarization Evaluation"¹⁰ introduces a new framework called DRPE (Diverse Role-Player Evaluation) that utilizes role prompting to assess text summarization quality. It leverages LLMs to simulate various role-players, both static (objective) and dynamic (subjective), to evaluate summaries across multiple subjective dimensions such as coherence, grammar, and interestingness. This method outperforms traditional metrics like BLEU/ROUGE by better aligning with human evaluations.

• "Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing?"¹¹ The paper explores the ability of LLMs to role-play and simulate persona-driven decision-making in complex scenarios, such as those found in novels. The authors introduce the NEXTDECISIONPREDICTION task and create the LIFECHOICE dataset, which includes key decision points from 1,401 characters in 395 books. The paper finds that while LLMs show promise in predicting decisions based on personas, there is room for improvement.

• "Persona is a Double-edged Sword: Enhancing the Zero-shot Reasoning by Ensembling the Role-playing and Neutral Prompts"¹² explores how role-playing personas can both help and hinder reasoning in LLMs. It proposes a framework called "Jekyll & Hyde" that combines results from both persona-based and neutral prompts to enhance the robustness of LLMs in reasoning tasks.

• "Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs"¹³ introduces a method called self-prompt tuning, which allows LLMs to generate their own role-play prompts through fine-tuning. By fine-tuning models like Mistral-7B and Llama-2-7B on a newly created LIMA-Role dataset, the models can automatically generate expert role-play prompts for different tasks, leading to improved performance on a range of NLP benchmarks.

Footnotes

1. Zheng, M., Pei, J., & Jurgens, D. (2023). Is “A Helpful Assistant” the Best Role for Large Language Models? A Systematic Evaluation of Social Roles in System Prompts. https://arxiv.org/abs/2311.10054 ↩ ↩² ↩³ ↩⁴

2. Wang, Z. M., Peng, Z., Que, H., Liu, J., Zhou, W., Wu, Y., Guo, H., Gan, R., Ni, Z., Yang, J., Zhang, M., Zhang, Z., Ouyang, W., Xu, K., Huang, S. W., Fu, J., & Peng, J. (2024). RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models. https://arxiv.org/abs/2310.00746 ↩

3. Kong, A., Zhao, S., Chen, H., Li, Q., Qin, Y., Sun, R., & Zhou, X. (2023). Better Zero-Shot Reasoning with Role-Play Prompting. ArXiv, abs/2308.07702. https://api.semanticscholar.org/CorpusID:260900230 ↩ ↩² ↩³ ↩⁴

4. Schmidt, D. C., Spencer-Smith, J., Fu, Q., & White, J. (2023). Cataloging Prompt Patterns to Enhance the Discipline of Prompt Engineering. https://api.semanticscholar.org/CorpusID:257368147 ↩

5. Wang, Z., Mao, S., Wu, W., Ge, T., Wei, F., & Ji, H. (2024). Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration. https://arxiv.org/abs/2307.05300 ↩

6. Reynolds, L., & McDonell, K. (2021). Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm. https://arxiv.org/abs/2102.07350 ↩ ↩² ↩³

7. Schulhoff, S. V. (2024). Is Role Prompting Effective? https://learnprompting.org/blog/2024/7/16/role_prompting ↩

8. Olea, C., Tucker, H., Phelan, J., Pattison, C., Zhang, S., Lieb, M., Schmidt, D., & White, J. (2024). Evaluating Persona Prompting for Question Answering Tasks. Security, Privacy and Trust Management. https://api.semanticscholar.org/CorpusID:270819947 ↩

9. Njifenjou, A., Sucal, V., Jabaian, B., & Lefèvre, F. (2024). Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation. https://arxiv.org/abs/2406.18460 ↩

10. Wu, N., Gong, M., Shou, L., Liang, S., & Jiang, D. (2023). Large Language Models are Diverse Role-Players for Summarization Evaluation. https://arxiv.org/abs/2303.15078 ↩

11. Xu, R., Wang, X., Chen, J., Yuan, S., Yuan, X., Liang, J., Chen, Z., Dong, X., & Xiao, Y. (2024). Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing? https://arxiv.org/abs/2404.12138 ↩

12. Kim, J., Yang, N., & Jung, K. (2024). Persona is a Double-edged Sword: Enhancing the Zero-shot Reasoning by Ensembling the Role-playing and Neutral Prompts. https://arxiv.org/abs/2408.08631 ↩

13. Kong, A., Zhao, S., Chen, H., Li, Q., Qin, Y., Sun, R., Zhou, X., Zhou, J., & Sun, H. (2024). Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs. https://arxiv.org/abs/2407.08995 ↩