42 citations · 59 across the 17 of their papers we have counts for
11 papers · 1 filter
SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
Yurun Chen, Zeyi Liao, Ping Yin +3
With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and irreversible consequences. Mos…
Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
Tianci Xue, Zeyi Liao, Tianneng Shi +5
Real-world digital environments are highly diverse and dynamic. These characteristics cause agents to frequently encounter unseen environments and distribution shifts, making conti…
Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs
Yurun Chen, Xavier Hu, Yuhan Liu +8
As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing t…
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Zeyi Liao, Jaylen Jones, Linxi Jiang +5
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection. Current evaluations of t…
AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts
Vishal Kumar, Zeyi Liao, Jaylen Jones +1
Although large language models (LLMs) are typically aligned, they remain vulnerable to jailbreaking through either carefully crafted prompts in natural language or, interestingly,…
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
Ziru Chen, Shijie Chen, Yuting Ning +17
The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked…
Introducing v0.5 of the AI Safety Benchmark from MLCommons
Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed +97
This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safe…
AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs
Zeyi Liao, Huan Sun
As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety…
AttributionBench: How Hard is Automatic Attribution Evaluation?
Yifei Li, Xiang Yue, Zeyi Liao +1
Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., wh…
A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents
Lingbo Mo, Zeyi Liao, Boyuan Zheng +3
Language agents powered by large language models (LLMs) have seen exploding development. Their capability of using language as a vehicle for thought and communication lends an incr…
ChatCounselor: A Large Language Models for Mental Health Support
June M. Liu, Donghao Li, He Cao +3
This paper presents ChatCounselor, a large language model (LLM) solution designed to provide mental health support. Unlike generic chatbots, ChatCounselor is distinguished by its f…