@inproceedings{rawte-etal-2025-document,
    title = "Document Attribution: Examining Citation Relationships using Large Language Models",
    author = "Rawte, Vipula  and
      Rossi, Ryan A.  and
      Dernoncourt, Franck  and
      Lipka, Nedim",
    editor = "Ghosal, Tirthankar  and
      Mayr, Philipp  and
      Singh, Amanpreet  and
      Naik, Aakanksha  and
      Rehm, Georg  and
      Freitag, Dayne  and
      Li, Dan  and
      Schimmler, Sonja  and
      De Waard, Anita",
    booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.sdp-1.12/",
    pages = "132--136",
    ISBN = "979-8-89176-265-7",
    abstract = "As Large Language Models (LLMs) are increasingly applied to document-based tasks - such as document summarization, question answering, and information extraction - where user requirements focus on retrieving information from provided documents rather than relying on the model{'}s parametric knowledge, ensuring the trustworthiness and interpretability of these systems has become a critical concern. A central approach to addressing this challenge is \textbf{attribution}, which involves tracing the generated outputs back to their source documents. However, since LLMs can produce inaccurate or imprecise responses, it is crucial to assess the reliability of these citations.To tackle this, our work proposes two techniques. (1) A \textbf{zero-shot} approach that frames attribution as a straightforward textual entailment task. Our method using flan-ul2 demonstrates an improvement of 0.27{\%} and 2.4{\%} over the best baseline of ID and OOD sets of AttributionBench (CITATION), respectively. (2) We also explore the role of the \textbf{attention mechanism} in enhancing the attribution process. Using a smaller LLM, flan-t5-small, the F1 scores outperform the baseline across almost all layers except layer 4 and layers 8 through 11."
}