@inproceedings{li-etal-2025-llmsr,
    title = "{LLMSR}@{XLLM}25: An Empirical Study of {LLM} for Structural Reasoning",
    author = "Li, Xinye  and
      Wan, Mingqi  and
      Sui, Dianbo",
    editor = "Fei, Hao  and
      Tu, Kewei  and
      Zhang, Yuhui  and
      Hu, Xiang  and
      Han, Wenjuan  and
      Jia, Zixia  and
      Zheng, Zilong  and
      Cao, Yixin  and
      Zhang, Meishan  and
      Lu, Wei  and
      Siddharth, N.  and
      {\O}vrelid, Lilja  and
      Xue, Nianwen  and
      Zhang, Yue",
    booktitle = "Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.xllm-1.30/",
    pages = "336--341",
    ISBN = "979-8-89176-286-2",
    abstract = "We present Team asdfo123{'}s submission to the XLLM@ACL 2025{--}LLM-SR shared task, which evaluates large language models on producing fine-grained, controllable, and interpretable reasoning processes. Systems must extract all problem conditions, decompose a chain of thought into statement{--}evidence pairs, and verify the logical validity of each pair. Leveraging only the off-the-shelf Meta-Llama-3-8B-Instruct, we craft a concise few-shot, multi-turn prompt that first enumerates all conditions and then guides the model to label, cite, and adjudicate every reasoning step. A lightweight post-processor based on regular expressions normalises spans and enforces the official JSON schema. Without fine-tuning, external retrieval, or ensembling, our method ranks 5th overall, achieving macro-$F_{1}$ scores on par with substantially more complex and resource-consuming pipelines. We conclude by analysing the strengths and limitations of our approach and outlining directions for future research in structural reasoning with LLMs. Our code is available at https://github.com/asdfo123/LLMSR-asdfo123"
}