9 papers
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation
Zhihao Ding, Jinming Li, Ze Lu +1
Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed binary classification task, impl…
Efficient and Effective Table-Centric Table Union Search in Data Lakes
Yongkang Sun, Zhihao Ding, Huiqiang Wang +2
In data lakes, information on the same subject is often fragmented across multiple tables. Table union search aims to find the top-k tables that can be unioned with a query table t…
Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
Xianglin Yang, Gelei Deng, Jieming Shi +2
Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses.…
Retrieve-and-Verify: A Table Context Selection Framework for Accurate Column Annotations
Zhihao Ding, Yongkang Sun, Jieming Shi
Tables are a prevalent format for structured data, yet their metadata, such as semantic types and column relationships, is often incomplete or ambiguous. Column annotation tasks, i…
Efficient Integration of Multi-View Attributed Graphs for Clustering and Embedding
Yiran Li, Gongyao Guo, Jieming Shi +2
A multi-view attributed graph (MVAG) G captures the diverse relationships and properties of real-world entities through multiple graph views and attribute views. Effectively utiliz…
Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges
Yiran Li, Gongyao Guo, Chen Feng +1
An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes. Attributed hypergraph node and hyperedge embedding (AHNEE) maps nodes…