Search Results for author:
Found 18 papers, 5 papers with code
Treasures Outside Contexts: Improving Event Detection via Global Statistics
Event detection (ED) aims at identifying event instances of specified types in given texts, which has been formalized as a sequence labeling task.
DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities.
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks yet still are vulnerable to external threats, particularly LLM Denial-of-Service (LLM-DoS) attacks.
Smaller Language Models Are Better Instruction Evolvers
In this study, we question this prevalent assumption and conduct an in-depth exploration into the potential of smaller language models (SLMs) in the context of instruction evolution.
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
To ensure that each specialized expert in the MoE model works as expected, we select a small amount of seed data that each expert excels to pre-optimize the router.
Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character Recognition
The study of oracle characters plays an important role in Chinese archaeology and philology.
Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content.
Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak."
Marginal Debiased Network for Fair Visual Recognition
Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair behavior and arising controversy in the modern pluralistic and egalitarian society.
Oracle Character Recognition using Unsupervised Discriminative Consistency Network
Ancient history relies on the study of ancient characters.
BitCoin: Bidirectional Tagging and Supervised Contrastive Learning based Joint Relational Triple Extraction Framework
To address these issues, we propose BitCoin, an innovative Bidirectional tagging and supervised Contrastive learning based joint relational triple extraction framework.
Quantifying and Analyzing Entity-level Memorization in Large Language Models
Quantifying language model memorization helps evaluate potential privacy risks.
A Self-supervised Mixed-curvature Graph Neural Network
Instead of working on one single constant-curvature space, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces and design hierarchical attention mechanisms for learning and fusing the representations across these component spaces.
Dense Contrastive Visual-Linguistic Pretraining
To overcome these issues, we propose unbiased Dense Contrastive Visual-Linguistic Pretraining (DCVLP), which replaces the region regression and classification with cross-modality region contrastive learning that requires no annotations.
Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions.
Contrastive Visual-Linguistic Pretraining
We evaluate CVLP on several down-stream tasks, including VQA, GQA and NLVR2 to validate the superiority of contrastive learning on multi-modality representation learning.
Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering
To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously.
Adaptive Noise Injection: A Structure-Expanding Regularization for RNN
Due to the adaptive noises can be improved as the training processes, its negative effects can be weakened and even transformed into a positive effect to further improve the expressiveness of the main-branch RNN.
