{"ID":2864867,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23501","arxiv_id":"2509.23501","title":"The Impact of Role Design in In-Context Learning for Large Language Models","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.23501","url_pdf":"https://arxiv.org/pdf/2509.23501v1","authors":"[\"Hamidreza Rouzegar\",\"Masoud Makrehchi\"]","published":"2025-09-27T21:15:30Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}