@inproceedings{jindal-etal-2025-offloaded,
    title = "Offloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement",
    author = "Jindal, Ishan  and
      Taneja, Jayant  and
      Chandana, Badrinath  and
      Kapur, Vikas  and
      Sharma, Sachin Dev",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.393/",
    doi = "10.18653/v1/2025.findings-emnlp.393",
    pages = "7450--7458",
    ISBN = "979-8-89176-335-7"
}