mlsanityData to 14 Oct 2026

The Impact of Role Design in In-Context Learning for Large Language Models

arXiv 2509.23501 ↗First posted 27 Sep 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 27 Sep 2025.

Builds on

27 of 33 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  7. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  10. 2022A Survey on In-context Learningcited by 721
  11. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  12. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 388
15 more
  1. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 268
  2. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  3. 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 216
  4. 2022Active Example Selection for In-Context Learningcited by 196
  5. 2022Instruction Induction: From Few Examples to Natural Language Task Descriptionscited by 152
  6. 2023In-context Pretraining: Language Modeling Beyond Document Boundariescited by 79
  7. 2023Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functionscited by 63
  8. 2020Investigating Societal Biases in a Poetry Composition Systemcited by 48
  9. 2023MoT: Memory-of-Thought Enables ChatGPT to Self-Improvecited by 38
  10. 2023Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Followingcited by 33
  11. 2023Generative AI Text Classification using Ensemble LLM Approachescited by 29
  12. 2024Enhancing Text Classification through LLM-Driven Active Learning and Human Annotationcited by 20
  13. 2024Task Facet Learning: A Structured Approach to Prompt Optimizationcited by 19
  14. 2024MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learningcited by 15
  15. 2024Generative AI for Enhancing Active Learning in Education: A Comparative Study of GPT-3.5 and GPT-4 in Crafting Customized Test Questionscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Order Matters: Rethinking Prompt Construction in In-Context Learning
  2. 2024Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning
  3. 2023The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
  4. 2023In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax
  5. 2024Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas
  6. 2024Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs
  7. 2025Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
  8. 2025Improving LLM Reasoning through Interpretable Role-Playing Steering