Due to the black-box nature of large language models (LLMs) and the realism of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement have become significant. In this context, sourcing information from multiple perspectives is essential. This survey presents a systematic investigation organized around four interrelated dimensions: Model Sourcing, Model Structure Sourcing, Training Data Sourcing, and External Data Sourcing. Moreover, a unified dual-paradigm taxonomy is proposed that classifies existing sourcing methods into prior-based (proactive traceability embedding) and posterior-based (retrospective inference) approaches. Traceability across these dimensions enhances the transparency, accountability, and trustworthiness of LLMs deployment in real-world applications.
@article{arxiv.2510.10161,
title = {Large Language Model Sourcing: A Survey},
author = {Liang Pang and Jia Gu and Sunhao Dai and Zihao Wei and Zenghao Duan and Kangxi Wu and Zhiyi Yin and Jun Xu and Huawei Shen and Xueqi Cheng},
journal= {arXiv preprint arXiv:2510.10161},
year = {2026}
}