The Impact of Role Design in In-Context Learning for Large Language Models
This work addresses the underexplored problem of role design in prompts for LLM users, but it appears incremental as it builds on existing prompt engineering research.
The study investigated how designing roles within prompts affects in-context learning for large language models, finding that role-based structuring can enhance performance across tasks like sentiment analysis and math reasoning.
In-context learning (ICL) enables Large Language Models (LLMs) to generate predictions based on prompts without additional fine-tuning. While prompt engineering has been widely studied, the impact of role design within prompts remains underexplored. This study examines the influence of role configurations in zero-shot and few-shot learning scenarios using GPT-3.5 and GPT-4o from OpenAI and Llama2-7b and Llama2-13b from Meta. We evaluate the models' performance across datasets, focusing on tasks like sentiment analysis, text classification, question answering, and math reasoning. Our findings suggest the potential of role-based prompt structuring to enhance LLM performance.