@inproceedings{zhang-etal-2026-resource,
title = "Resource Consumption Threats in Large Language Models: A Survey",
author = "Zhang, Yuanhe and
Wang, Xinyue and
Chen, Zhican and
Wang, Weiliu and
Zhang, Zilu and
Gong, Zhengshuo and
Zhou, Zhenhong and
Wang, Kun and
Sun, Li and
Liu, Yang and
Su, Sen",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1444/",
pages = "32962--32992",
ISBN = "979-8-89176-459-0",
abstract = "Resource utilization has been studied as an optimization objective for generative large language models (LLMs). Recent studies show that this resource dependence can also be weaponized, as excessive generation, when scaled through high-volume requests, increases inference latency, undermines service availability, and threatens economic sustainability. However, these risks remain underexamined because existing studies are fragmented and their boundaries with legitimate, resource-intensive uses of LLMs are unclear. To address this gap, we provide a systematic review of threats to resource consumption in LLMs. Unlike surveys on inference acceleration, we focus on how resource consumption threats induce disruptive behaviors and synthesize existing studies into research strands that connect attack objectives, triggering mechanisms, and defenses. We further introduce an outcome-based severity taxonomy that distinguishes bounded, non-degenerate Overthinking from self-sustaining Unbounded Drift, providing operational criteria for characterizing adversarial resource consumption. Our goal is to clarify this emerging threat landscape and support future characterization, evaluation, and mitigation. The project repository is publicly available at https://anonymous.4open.science/r/RCT-LLM/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-resource">
<titleInfo>
<title>Resource Consumption Threats in Large Language Models: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanhe</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhican</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiliu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengshuo</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Resource utilization has been studied as an optimization objective for generative large language models (LLMs). Recent studies show that this resource dependence can also be weaponized, as excessive generation, when scaled through high-volume requests, increases inference latency, undermines service availability, and threatens economic sustainability. However, these risks remain underexamined because existing studies are fragmented and their boundaries with legitimate, resource-intensive uses of LLMs are unclear. To address this gap, we provide a systematic review of threats to resource consumption in LLMs. Unlike surveys on inference acceleration, we focus on how resource consumption threats induce disruptive behaviors and synthesize existing studies into research strands that connect attack objectives, triggering mechanisms, and defenses. We further introduce an outcome-based severity taxonomy that distinguishes bounded, non-degenerate Overthinking from self-sustaining Unbounded Drift, providing operational criteria for characterizing adversarial resource consumption. Our goal is to clarify this emerging threat landscape and support future characterization, evaluation, and mitigation. The project repository is publicly available at https://anonymous.4open.science/r/RCT-LLM/.</abstract>
<identifier type="citekey">zhang-etal-2026-resource</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1444/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>32962</start>
<end>32992</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Resource Consumption Threats in Large Language Models: A Survey
%A Zhang, Yuanhe
%A Wang, Xinyue
%A Chen, Zhican
%A Wang, Weiliu
%A Zhang, Zilu
%A Gong, Zhengshuo
%A Zhou, Zhenhong
%A Wang, Kun
%A Sun, Li
%A Liu, Yang
%A Su, Sen
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-resource
%X Resource utilization has been studied as an optimization objective for generative large language models (LLMs). Recent studies show that this resource dependence can also be weaponized, as excessive generation, when scaled through high-volume requests, increases inference latency, undermines service availability, and threatens economic sustainability. However, these risks remain underexamined because existing studies are fragmented and their boundaries with legitimate, resource-intensive uses of LLMs are unclear. To address this gap, we provide a systematic review of threats to resource consumption in LLMs. Unlike surveys on inference acceleration, we focus on how resource consumption threats induce disruptive behaviors and synthesize existing studies into research strands that connect attack objectives, triggering mechanisms, and defenses. We further introduce an outcome-based severity taxonomy that distinguishes bounded, non-degenerate Overthinking from self-sustaining Unbounded Drift, providing operational criteria for characterizing adversarial resource consumption. Our goal is to clarify this emerging threat landscape and support future characterization, evaluation, and mitigation. The project repository is publicly available at https://anonymous.4open.science/r/RCT-LLM/.
%U https://aclanthology.org/2026.emnlp-main.1444/
%P 32962-32992
Markdown (Informal)
[Resource Consumption Threats in Large Language Models: A Survey](https://aclanthology.org/2026.emnlp-main.1444/) (Zhang et al., EMNLP 2026)
ACL
- Yuanhe Zhang, Xinyue Wang, Zhican Chen, Weiliu Wang, Zilu Zhang, Zhengshuo Gong, Zhenhong Zhou, Kun Wang, Li Sun, Yang Liu, and Sen Su. 2026. Resource Consumption Threats in Large Language Models: A Survey. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 32962–32992, Budapest, Hungary. Association for Computational Linguistics.