@inproceedings{naik-etal-2025-programming,
    title = "Programming by Example meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction",
    author = "Naik, Atharva  and
      Agrawal, Darsh  and
      Sng, Hong  and
      Marr, Clayton  and
      Zhang, Kexun  and
      Robinson, Nathaniel Romney  and
      Chang, Kalvin  and
      Byrnes, Rebecca  and
      Mysore, Aravind  and
      Rose, Carolyn  and
      Mortensen, David R.",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1432/",
    pages = "29628--29647",
    ISBN = "979-8-89176-251-0",
    abstract = "Historical linguists have long written ``programs'' that convert reconstructed words in an ancestor language into their attested descendants via ordered string rewrite functions (called sound laws) However, writing these programs is time-consuming, motivating the development of automated Sound Law Induction (SLI) which we formulate as Programming by Examples (PBE) with Large Language Models (LLMs) in this paper. While LLMs have been effective for code generation, recent work has shown that PBE is challenging but improvable by fine-tuning, especially with training data drawn from the same distribution as evaluation data. In this paper, we create a conceptual framework of what constitutes a ``similar distribution'' for SLI and propose four kinds of synthetic data generation methods with varying amounts of inductive bias to investigate what leads to the best performance. Based on the results, we create a SOTA open-source model for SLI as PBE (+6{\%} pass rate with a third of the parameters of the second-best LLM) and also highlight exciting future directions for PBE research."
}