@inproceedings{chen-etal-2024-mothman,
    title = "Mothman at {S}em{E}val-2024 Task 9: An Iterative System for Chain-of-Thought Prompt Optimization",
    author = "Chen, Alvin Po-Chun  and
      Groshan, Ray  and
      von Bayern, Sean",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.semeval-1.263/",
    doi = "10.18653/v1/2024.semeval-1.263",
    pages = "1876--1888",
    abstract = "Extensive research exists on the performance of large language models on logic-based tasks, whereas relatively little has been done on their ability to generate creative solutions on lateral thinking tasks. The BrainTeaser shared task tests lateral thinking and uses adversarial datasets to prevent memorization, resulting in poor performance for out-of-the-box models. We propose a system for iterative, chain-of-thought prompt engineering which optimizes prompts using human evaluation. Using this shared task, we demonstrate our system{'}s ability to significantly improve model performance by optimizing prompts and evaluate the input dataset."
}