6 papers
Evaluating AI Meeting Summaries with a Reusable Cross-Domain Pipeline
Philip Zhong, Don Wang, Jason Zhang
Industrial teams often deploy large language model features before stable regression or model selection evaluation exists. We present a reusable evaluation system for AI meeting su…
A Survey of Secure Retrieval-Augmented Generation
Yuming Xu, Mingtao Zhang, Zhuohan Ge +7
Retrieval-augmented generation (RAG) improves large language models (LLMs) with external knowledge, but this access path creates security risks distinct from inherent prompt-only o…
The Structural Safety Generalization Problem
Julius Broomfield, Tom Gibbs, Ethan Kosak-Hine +7
LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize a…
OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Tasks
Haoyang Li, Yuming Xu, Alexander Zhou +4
Graphs are fundamental data structures for modeling complex interactions in domains such as social networks, molecular structures, and biological systems. Graph-level tasks, which…
Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
Tom Gibbs, Ethan Kosak-Hine, George Ingebretsen +6
Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as mo…
Tight Lower Bounds for Directed Cut Sparsification and Distributed Min-Cut
Yu Cheng, Max Li, Honghao Lin +3
In this paper, we consider two fundamental cut approximation problems on large graphs. We prove new lower bounds for both problems that are optimal up to logarithmic factors. The f…