@inproceedings{shum-etal-2023-automatic,
    title = "Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data",
    author = "Shum, Kashun  and
      Diao, Shizhe  and
      Zhang, Tong",
    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-Cong-Liu-Florida-Atlantic-University-author-id/2023.findings-emnlp.811/",
    doi = "10.18653/v1/2023.findings-emnlp.811",
    pages = "12113--12139",
    abstract = "Chain-of-thought (CoT) advances the reasoning abilities of large language models (LLMs) and achieves superior performance in complex reasoning tasks. However, most CoT studies rely on carefully designed human-annotated rational chains to prompt LLMs, posing challenges for real-world applications where labeled data is available without rational chains. This paper proposes a new strategy, AutomateCoT (Automatic Prompt Augmentation and Selection with Chain-of-Thought), that can bypass human engineering of CoT by automatically augmenting rational chains from a small labeled dataset, and then pruning low-quality chains to construct a candidate pool of machinegenerated rationale chains based on the labels. Finally, it selects the optimal combination of several rationale chains from the pool for CoT prompting by employing a variance-reduced policy gradient strategy to estimate the significance of each example. Automate-CoT enables a quick adaptation of the CoT technique to different tasks. Experimental results demonstrate the effectiveness of our method, where competitive results are achieved on arithmetic reasoning (+2.7{\%}), commonsense reasoning (+3.4{\%}), symbolic reasoning (+3.2{\%}), and non-reasoning tasks (+2.5{\%})."
}