activity
20232026
most citedAutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

11 citations · 18 across the 15 of their papers we have counts for

collaborators
Showing 2024Show all

6 papers · 1 filter

cs.CL2024

Memory-Augmented Agent Training for Business Document Understanding

Jiale Liu, Yifan Zeng, Malte Højmark-Bertelsen +3

Traditional enterprises face significant challenges in processing business documents, where tasks like extracting transport references from invoices remain largely manual despite t…

cs.IR2024

LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking

Yifan Zeng, Ojas Tendolkar, Raymond Baartmans +3

Ranking passages by prompting a large language model (LLM) can achieve promising performance in modern information retrieval (IR) systems. A common approach to sort the ranking lis…

cs.CL2024

Assessing and Verifying Task Utility in LLM-Powered Applications

Negar Arabzadeh, Siqing Huo, Nikhil Mehta +5

The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks.…

cs.LG2024

Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search

Zachary Coalson, Huazheng Wang, Qingyun Wu +1

We study the robustness of data-centric methods to find neural network architectures, known as neural architecture search (NAS), against data poisoning. To audit this robustness, w…

cs.AI2024★ 6 cited

Embodied LLM Agents Learn to Cooperate in Organized Teams

Xudong Guo, Kaixuan Huang, Jiale Liu +6

Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-r…

cs.LG2024★ 11 cited

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Yifan Zeng, Yiran Wu, Xiao Zhang +2

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we…