4 papers
What Matters to an LLM? Behavioral and Computational Evidences from Summarization
Yongxin Zhou, Changshun Wu, Philippe Mulhem +2
Large Language Models (LLMs) are now state-of-the-art at summarization, yet the internal notion of importance that drives their information selections remains hidden. We propose to…
Randomized Smoothing Meets Vision-Language Models
Emmanouil Seferis, Changshun Wu, Stefanos Kollias +2
Randomized smoothing (RS) is one of the prominent techniques to ensure the correctness of machine learning models, where point-wise robustness certificates can be derived analytica…
LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers
Changshun Wu, Tianyi Duan, Saddek Bensalem +1
Fine-tuning large language models (LLMs) improves performance on domain-specific tasks but can lead to overfitting, making them unreliable on out-of-distribution (OoD) queries. We…
Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm
Changshun Wu, Weicheng He, Chih-Hong Cheng +2
Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models, often triggering overconfident predictions on non-target objects. While prior work has primari…