English
Related papers

Related papers: Efficient LLM Safety Evaluation through Multi-Agen…

200 papers

Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the research on cognitive behaviors of LLMs to explore human-like…

Computation and Language · Computer Science 2024-10-10 Tian Liang , Zhiwei He , Wenxiang Jiao , Xing Wang , Yan Wang , Rui Wang , Yujiu Yang , Shuming Shi , Zhaopeng Tu

As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that operate as…

Computation and Language · Computer Science 2024-05-27 Alex Kim , Keonwoo Kim , Sangwon Yoon

With the rapid development of Large Language Models (LLMs), increasing attention has been paid to their safety concerns. Consequently, evaluating the safety of LLMs has become an essential task for facilitating the broad applications of…

Computation and Language · Computer Science 2024-06-25 Zhexin Zhang , Leqi Lei , Lindong Wu , Rui Sun , Yongkang Huang , Chong Long , Xiao Liu , Xuanyu Lei , Jie Tang , Minlie Huang

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…

Artificial Intelligence · Computer Science 2026-02-03 Hanjun Luo , Shenyu Dai , Chiming Ni , Xinfeng Li , Guibin Zhang , Kun Wang , Tongliang Liu , Hanan Salam

Large Language Models (LLMs) demonstrate strong conversational abilities. In this Working Paper, we study them in the context of debating in two ways: their ability to perform in a structured debate along with a dataset of arguments to use…

Information Retrieval · Computer Science 2025-07-15 Anthony Miyaguchi , Conor Johnston , Aaryan Potdar

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Computation and Language · Computer Science 2025-03-19 Dong Shu , Chong Zhang , Mingyu Jin , Zihao Zhou , Lingyao Li , Yongfeng Zhang

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Cryptography and Security · Computer Science 2025-09-05 Chuhan Zhang , Ye Zhang , Bowen Shi , Yuyou Gan , Tianyu Du , Shouling Ji , Dazhan Deng , Yingcai Wu

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…

Cryptography and Security · Computer Science 2025-06-10 Yingchaojie Feng , Zhizhang Chen , Zhining Kang , Sijia Wang , Haoyu Tian , Wei Zhang , Minfeng Zhu , Wei Chen

Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority…

Artificial Intelligence · Computer Science 2026-05-14 Tommaso Giovannelli , Griffin D. Kent

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

Computation and Language · Computer Science 2026-02-17 Hanjiang Hu , Alexander Robey , Changliu Liu

Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) services due to their exceptional proficiency in understanding and generating human-like text. LLM chatbots, in particular, have seen widespread adoption,…

Cryptography and Security · Computer Science 2024-02-14 Gelei Deng , Yi Liu , Yuekang Li , Kailong Wang , Ying Zhang , Zefeng Li , Haoyu Wang , Tianwei Zhang , Yang Liu

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

Cryptography and Security · Computer Science 2023-10-05 Bocheng Chen , Advait Paliwal , Qiben Yan

Phishing attacks remain a critical cybersecurity threat. Attackers constantly refine their methods, making phishing emails harder to detect. Traditional detection methods, including rule-based systems and supervised machine learning models,…

Multiagent Systems · Computer Science 2025-07-01 Ngoc Tuong Vy Nguyen , Felix D Childress , Yunting Yin

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Cryptography and Security · Computer Science 2025-06-10 Yukai Zhou , Sibei Yang , Wenjie Wang

While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve…

Computation and Language · Computer Science 2024-01-12 Steffi Chern , Zhen Fan , Andy Liu

Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they…

Trading and Market Microstructure · Quantitative Finance 2025-11-06 Haofei Yu , Fenghai Li , Jiaxuan You

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Artificial Intelligence · Computer Science 2026-04-29 John Seon Keun Yi , Aaron Mueller , Dokyun Lee

Large Language Models (LLMs) need to adapt their predictions to diverse cultural contexts to benefit diverse communities across the world. While previous efforts have focused on single-LLM, single-turn approaches, we propose to exploit the…

Computation and Language · Computer Science 2025-09-03 Dayeon Ki , Rachel Rudinger , Tianyi Zhou , Marine Carpuat

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…