4 papers
Failing to Explore: Language Models on Interactive Tasks
Mahdi JafariRaviz, Keivan Rezaei, Arshia Soltani Moakhar +3
We evaluate language models on their ability to explore interactive environments under a limited interaction budget. We introduce three parametric tasks with controllable explorati…
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi +2
The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated te…
DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors
Yize Cheng, Wenxiao Wang, Mazda Moayeri +1
Open benchmarks are essential for evaluating and advancing large language models, offering reproducibility and transparency. However, their accessibility makes them likely targets…
Tool Preferences in Agentic LLMs are Unreliable
Kazem Faghih, Wenxiao Wang, Yize Cheng +5
Large language models (LLMs) can now access a wide range of external tools, thanks to the Model Context Protocol (MCP). This greatly expands their abilities as various agents. Howe…