5 papers
Agentao: A Policy-Governed Runtime Harness for Embeddable Tool-Using LLM Agents
Bo Jin, Qiang Jiao, Xin Tong
LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols. These capabilities make age…
Multi-Head Spectral-Adaptive Graph Anomaly Detection
Qingyue Cao, Bo Jin, Changwei Gong +3
Graph anomaly detection technology has broad applications in financial fraud and risk control. However, existing graph anomaly detection methods often face significant challenges w…
HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
Xin Tong, Zhi Lin, Jingya Wang +1
Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: hea…
MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors
Xin Tong, Zhi Lin, Jingya Wang +2
Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and ot…
CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain
Xin Tong, Bo Jin, Zhi Lin +3
Large Language Models (LLMs) have demonstrated significant potential and effectiveness across multiple application domains. To assess the performance of mainstream LLMs in public s…