6 papers
SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent Systems
Ruxue Shi, Yili Wang, Mengnan Du +4
LLM-based multi-agent systems (MAS) solve complex tasks through inter-agent collaboration, but their communication-driven nature also allows security risks to spread across agents…
TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning
Ruxue Shi, Yili Wang, Mengnan Du +3
Few-shot tabular learning provides a cost-effective approach for real-world applications where annotation is costly and collecting sufficient samples for new tasks is difficult. Ex…
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
Jingyi He, Haiyan Zhao, Ruxue Shi +4
Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features…
A Comprehensive Survey of Synthetic Tabular Data Generation
Ruxue Shi, Yili Wang, Mengnan Du +3
Tabular data is one of the most prevalent and important data formats in real-world applications such as healthcare, finance, and education. However, its effective use in machine le…
Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification
Ruxue Shi, Hengrui Gu, Xu Shen +1
Large Language Models (LLMs) have shown remarkable ability in solving complex tasks, making them a promising tool for enhancing tabular learning. However, existing LLM-based method…
Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning
Ruxue Shi, Hengrui Gu, Hangting Ye +3
Few-shot tabular learning, in which machine learning models are trained with a limited amount of labeled data, provides a cost-effective approach to addressing real-world challenge…