12 papers
When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse
Yingtao Ren, Ziyi Zhao, Yiwei Fu +3
Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial doc…
Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction
Jiazhen Huang, Zhiming Liu, Changhu Wang +3
A range of methods aim to enhance the performance of vision-language models (VLMs) at test time. Among them, transduction has emerged as a promising paradigm due to its strong comp…
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions
Zhiyin Yu, Yuchen Mou, Juncheng Yan +17
Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, reinforcement learni…
DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise
Yusheng Zhao, Jiaye Xie, Qixin Zhang +5
Graph neural networks (GNNs) have been widely used in various graph machine learning scenarios. Existing literature primarily assumes well-annotated training graphs, while the reli…
A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges
Wei Ju, Siyu Yi, Yifan Wang +10
Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and netwo…
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives
Junyu Luo, Bohan Wu, Xiao Luo +8
Post-training of Large Language Models (LLMs) is crucial for unlocking their task generalization potential and domain-specific capabilities. However, the current LLM post-training…