4 papers · 1 filter
URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
Vinh Nguyen, Cuong Dang, Jiahao Zhang +6
Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluati…
What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs
Aakriti Shah, Yifan Hu, Thai Le
Unlearning in large language models (LLMs) is usually evaluated as whether an "unlearned" fact can be recovered. We instead ask whether a fact's structural entanglement with the re…
Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting
Bang Trinh Tran To, Thai Le
This work presents LURK (Latent UnleaRned Knowledge), a novel framework that probes for hidden retained knowledge in unlearned LLMs through adversarial suffix prompting. LURK autom…
RMDM: A Multilabel Fakenews Dataset for Vietnamese Evidence Verification
Hai-Long Nguyen, Thi-Kieu-Trang Pham, Thai-Son Le +3
In this study, we present a novel and challenging multilabel Vietnamese dataset (RMDM) designed to assess the performance of large language models (LLMs), in verifying electronic i…