14 papers · 1 filter
DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
Yibo Yan, Guangwei Xu, Xin Zou +3
Visual Document Retrieval (VDR), the task of retrieving visually-rich document pages using queries that combine visual and textual cues, is crucial for numerous real-world applicat…
CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
Yu Zhang, Shuliang Liu, Xu Yang +1
Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, suc…
PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
Jiahao Huo, Shuliang Liu, Bin Wang +5
Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as…
Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms
Zipeng Ling, Shuliang Liu, Yuehao Tang +8
Large Language Models (LLMs) annotated datasets are widely used nowadays, however, large-scale annotations often show biases in low-quality datasets. For example, Multiple-Choice Q…
Unlocking Speech Instruction Data Potential with Query Rewriting
Yonghua Hei, Yibo Yan, Shuliang Liu +3
End-to-end Large Speech Language Models~(\textbf{LSLMs}) demonstrate strong potential in response latency and speech comprehension capabilities, showcasing general intelligence acr…
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
Shuliang Liu, Hongyi Liu, Aiwei Liu +7
The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditi…
LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
Zipeng Ling, Shuliang Liu, Yuehao Tang +8
Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misapplied: in real-world applicatio…
VLA-Mark: A cross modal watermark for large vision-language alignment model
Shuliang Liu, Qi Zheng, Jesse Jiaxi Xu +8
Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual…
Video Signature: Implicit Watermarking for Video Diffusion Models
Yu Huang, Junhao Chen, Shuliang Liu +6
The rapid development of Artificial Intelligence Generated Content (AIGC) has led to significant progress in video generation, but also raises serious concerns about intellectual p…
Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities
Junyan Zhang, Yubo Gao, Yibo Yan +8
The finetuning of Large Language Models (LLMs) has significantly advanced their instruction-following capabilities, yet the underlying computational mechanisms driving these improv…
Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?
Junyan Zhang, Yiming Huang, Shuliang Liu +2
The rapid adoption of LLMs has overshadowed the potential advantages of traditional BERT-like models in text classification. This study challenges the prevailing "LLM-centric" tren…
CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality
Junyan Zhang, Shuliang Liu, Aiwei Liu +4
Watermarking technology is a method used to trace the usage of content generated by large language models. Sentence-level watermarking aids in preserving the semantic integrity wit…
TreeHop: Efficient Embedding-Level Query Rewriter
Zhonghao Li, Kunpeng Zhang, Jinghuai Ou +2
Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multi…
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
Junkai Chen, Zhijie Deng, Kening Zheng +6
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forge…