@inproceedings{dong-etal-2026-large,
title = "On Large Language Models for Effective Red Teaming",
author = "Dong, Ming and
Ren, Hongjing and
Zheng, Bolong and
Wang, Chengji and
Cai, Jingwen and
Chen, Guanyi and
He, Tingting",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1155/",
pages = "24436--24453",
ISBN = "979-8-89176-462-0",
abstract = "Red teaming attacks are a well-established approach for identifying weaknesses in large language models (LLMs). As the generative capabilities of LLMs continue to improve, researchers have increasingly leveraged them to automatically generate red teaming attacks, often by crafting adversarial prompts that target other LLMs. Despite this progress, there is currently no effective strategy for selecting suitable LLMs to serve as red teaming agents. In this work, we propose a systematic framework to investigate how various factors of LLMs influence their effectiveness in generating red teaming attacks, including model security, general capability, and parameter scale. The goal of this study is to understand the mechanisms behind the effectiveness of red teaming LLMs and to provide principled guidance for selecting appropriate red teaming LLM."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2026-large">
<titleInfo>
<title>On Large Language Models for Effective Red Teaming</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongjing</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bolong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengji</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwen</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">He</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Red teaming attacks are a well-established approach for identifying weaknesses in large language models (LLMs). As the generative capabilities of LLMs continue to improve, researchers have increasingly leveraged them to automatically generate red teaming attacks, often by crafting adversarial prompts that target other LLMs. Despite this progress, there is currently no effective strategy for selecting suitable LLMs to serve as red teaming agents. In this work, we propose a systematic framework to investigate how various factors of LLMs influence their effectiveness in generating red teaming attacks, including model security, general capability, and parameter scale. The goal of this study is to understand the mechanisms behind the effectiveness of red teaming LLMs and to provide principled guidance for selecting appropriate red teaming LLM.</abstract>
<identifier type="citekey">dong-etal-2026-large</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1155/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>24436</start>
<end>24453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Large Language Models for Effective Red Teaming
%A Dong, Ming
%A Ren, Hongjing
%A Zheng, Bolong
%A Wang, Chengji
%A Cai, Jingwen
%A Chen, Guanyi
%A He, Tingting
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F dong-etal-2026-large
%X Red teaming attacks are a well-established approach for identifying weaknesses in large language models (LLMs). As the generative capabilities of LLMs continue to improve, researchers have increasingly leveraged them to automatically generate red teaming attacks, often by crafting adversarial prompts that target other LLMs. Despite this progress, there is currently no effective strategy for selecting suitable LLMs to serve as red teaming agents. In this work, we propose a systematic framework to investigate how various factors of LLMs influence their effectiveness in generating red teaming attacks, including model security, general capability, and parameter scale. The goal of this study is to understand the mechanisms behind the effectiveness of red teaming LLMs and to provide principled guidance for selecting appropriate red teaming LLM.
%U https://aclanthology.org/2026.findings-emnlp.1155/
%P 24436-24453
Markdown (Informal)
[On Large Language Models for Effective Red Teaming](https://aclanthology.org/2026.findings-emnlp.1155/) (Dong et al., Findings 2026)
ACL
- Ming Dong, Hongjing Ren, Bolong Zheng, Chengji Wang, Jingwen Cai, Guanyi Chen, and Tingting He. 2026. On Large Language Models for Effective Red Teaming. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 24436–24453, Budapest, Hungary. Association for Computational Linguistics.