6 papers
Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
Bing Liu, Shunping Wang, Yufan Zhu +5
This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language…
Understanding Generalization through Decision Pattern Shift
Huiqi Deng, Yibo Li, Quanshi Zhang +3
Understanding why deep neural networks (DNNs) fail to generalize to unseen samples remains a long-standing challenge. Existing studies mainly examine changes in externally observab…
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
Jie Ma, Ning Qu, Zhitao Gao +8
Knowledge graph-based retrieval-augmented generation seeks to mitigate hallucinations in Large Language Models (LLMs) caused by insufficient or outdated knowledge. However, existin…
The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation
Huiqi Deng, Qihan Ren, Zhuofan Chen +5
Understanding what kinds of cooperative structures deep neural networks (DNNs) can represent remains a fundamental yet insufficiently understood problem. In this work, we treat int…
Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
Huiqi Deng, Hongbin Pei, Quanshi Zhang +1
Attribution explanation is a typical approach for explaining deep neural networks (DNNs), inferring an importance or contribution score for each input variable to the final output.…
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
Jie Ma, Min Hu, Pinghui Wang +5
Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video…