@inproceedings{lin-etal-2025-llm,
    title = "On {LLM}-Based Scientific Inductive Reasoning Beyond Equations",
    author = "Lin, Brian S.  and
      Yuan, Jiaxin  and
      Zhou, Zihan  and
      Wang, Shouli  and
      Wang, Shuo  and
      Kong, Cunliang  and
      Shi, Qi  and
      Li, Yuxuan  and
      Yang, Liner  and
      Liu, Zhiyuan  and
      Sun, Maosong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.476/",
    pages = "9382--9405",
    ISBN = "979-8-89176-332-6",
    abstract = "As large language models (LLMs) increasingly exhibit human-like capabilities, a fundamental question emerges: How can we enable LLMs to learn the underlying patterns from limited examples in entirely novel environments and apply them effectively? This question is central to the ability of LLMs in inductive reasoning. Existing research on LLM-based inductive reasoning can be broadly categorized based on whether the underlying rules are expressible via explicit mathematical equations. However, many recent studies in the beyond-equations category have emphasized rule design without grounding them in specific scenarios. Inspired by the parallels between inductive reasoning and human scientific discovery, we propose the task of LLM-Based Scientific Inductive Reasoning Beyond Equations and introduce a new benchmark, SIRBench-V1, to evaluate the inductive reasoning abilities of LLMs in scientific settings. Our experimental results show that current LLMs still struggle with this task, underscoring its difficulty and the need for further advancement in this area."
}