Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent resource consumption threats induce excessive generation, degrading model efficiency and harming both service availability and economic sustainability. This survey presents a systematic review of threats to resource consumption in LLMs. We further establish a unified view of this emerging area by clarifying its scope and examining the problem along the full pipeline from threat induction to mechanism understanding and mitigation. Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.
@article{arxiv.2603.16068,
title = {Resource Consumption Threats in Large Language Models},
author = {Yuanhe Zhang and Xinyue Wang and Zhican Chen and Weiliu Wang and Zilu Zhang and Zhengshuo Gong and Zhenhong Zhou and Kun Wang and Li Sun and Yang Liu and Sen Su},
journal= {arXiv preprint arXiv:2603.16068},
year = {2026}
}