Large Language Model Sourcing: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pang, Liang, Gu, Jia, Dai, Sunhao, Wei, Zihao, Duan, Zenghao, Wu, Kangxi, Yin, Zhiyi, Xu, Jun, Shen, Huawei, Cheng, Xueqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911346240520192
author Pang, Liang
Gu, Jia
Dai, Sunhao
Wei, Zihao
Duan, Zenghao
Wu, Kangxi
Yin, Zhiyi
Xu, Jun
Shen, Huawei
Cheng, Xueqi
author_facet Pang, Liang
Gu, Jia
Dai, Sunhao
Wei, Zihao
Duan, Zenghao
Wu, Kangxi
Yin, Zhiyi
Xu, Jun
Shen, Huawei
Cheng, Xueqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10161
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Model Sourcing: A Survey
Pang, Liang
Gu, Jia
Dai, Sunhao
Wei, Zihao
Duan, Zenghao
Wu, Kangxi
Yin, Zhiyi
Xu, Jun
Shen, Huawei
Cheng, Xueqi
Computation and Language
Artificial Intelligence
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.
title Large Language Model Sourcing: A Survey
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.10161