30 papers
EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation
Sihang Jia, Shuliang Liu, Songbo Yang +1
Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is primarily incorporated into answ…
AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval
Haoyu Zuo, Yibo Yan, Xin Zou +4
Multi-vector vision-language retrievers enable fine-grained Visual Document Retrieval (VDR) through late interaction, but storing and scoring hundreds of visual patch embeddings pe…
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
Xin Zou, Haolin Deng, Yibo Yan +5
Multimodal Large Language Models (MLLMs) are prone to hallucination as their generation preferences are insufficiently calibrated to visual evidence, causing them to fall back on l…
Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning
Xin Zou, Haolin Deng, Yibo Yan +6
Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cross-view consistency, \texti…
Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
Sihang Jia, Shuliang Liu, Songbo Yang +3
Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigat…
Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
Yibo Yan, Mingdong Ou, Yi Cao +5
Multi-vector models dominate Visual Document Retrieval (VDR) due to their fine-grained matching capabilities, but their high storage and computational costs present a major barrier…
Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
Zipeng Ling, Shuliang Liu, Seonil Son +4
Large language models (LLMs) have become increasingly used for various tasks, often coupled with Chain-of-Thought (CoT) prompting to boost accuracy. Recent work has shown that high…
Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
Yibo Yan, Mingdong Ou, Yi Cao +6
Harnessing the full potential of visually-rich documents requires retrieval systems that understand not just text, but intricate layouts, a core challenge in Visual Document Retrie…
Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
Yibo Yan, Jiahao Huo, Guanbo Feng +12
With the rapid proliferation of multimodal information, Visual Document Retrieval (VDR) has emerged as a critical frontier in bridging the gap between unstructured visually rich da…
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
Yibo Yan, Mingdong Ou, Yi Cao +5
Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applicatio…
A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model
Qi Zheng, Shuliang Liu, Yu Huang +8
Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in Large Vision-Language Models (LVLMs). However, vision-agnostic water…
Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
Shuliang Liu, Songbo Yang, Dong Fang +7
Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models b…
Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models
Shuliang Liu, Xingyu Li, Hongyi Liu +6
Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur…
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…