2 papers
cs.CL2026
FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection
Y. H. Zhou, Z. M. Ma, Y. J. Zhou +12
SMS fraud is increasingly cross-channel: a message directs the user to a webpage, and the final risk depends on how the SMS claim aligns with the page content and requested user ac…
cs.CL2025
Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework
Zucheng Liang, Wenxin Wei, Kaijie Zhang +1
Accurately answering complex questions has consistently been a significant challenge for Large Language Models (LLMs). To address this, this paper proposes a multi-hop question dec…