4 papers
Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning
Austin MY Cheung, Yi Yang
Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We investigate a related but distinct f…
RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledge
Jiale Han, Austin Cheung, Yubai Wei +4
Knowledge is inherently time-sensitive and continuously evolves over time. Although current Retrieval-Augmented Generation (RAG) systems enrich LLMs with external knowledge, they l…
HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image Models
Zhihao Zhu, Jiale Han, Yi Yang
Image-based AI models are increasingly deployed across a wide range of domains, including healthcare, security, and consumer applications. However, many image datasets carry sensit…
Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval
Yubai Wei, Jiale Han, Yi Yang
Text embedding models play a cornerstone role in AI applications, such as retrieval-augmented generation (RAG). While general-purpose text embedding models demonstrate strong perfo…