@inproceedings{loya-etal-2023-exploring,
    title = "Exploring the Sensitivity of {LLM}s' Decision-Making Capabilities: Insights from Prompt Variations and Hyperparameters",
    author = "Loya, Manikanta  and
      Sinha, Divya  and
      Futrell, Richard",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.findings-emnlp.241/",
    doi = "10.18653/v1/2023.findings-emnlp.241",
    pages = "3711--3716",
    abstract = "The advancement of Large Language Models (LLMs) has led to their widespread use across a broad spectrum of tasks, including decision-making. Prior studies have compared the decision-making abilities of LLMs with those of humans from a psychological perspective. However, these studies have not always properly accounted for the sensitivity of LLMs' behavior to hyperparameters and variations in the prompt. In this study, we examine LLMs' performance on the Horizon decision-making task studied by Binz and Schulz (2023), analyzing how LLMs respond to variations in prompts and hyperparameters. By experimenting on three OpenAI language models possessing different capabilities, we observe that the decision-making abilities fluctuate based on the input prompts and temperature settings. Contrary to previous findings, language models display a human-like exploration{--}exploitation tradeoff after simple adjustments to the prompt."
}