Jingyu Zhang
2 papers · Latest:
Human-Computer Interaction
Making Sense of Scams: Understanding Scam Conversations Through Multi-Level Alignment
This paper introduces multi-level alignment-based hints to detect online scams in conversations, showing high-level alignment declines as scams progress.
2604.23973
Natural Language ProcessingMany-Tier Instruction Hierarchy in LLM Agents
This paper introduces ManyIH, a new paradigm and benchmark (ManyIH-Bench) to help LLM agents resolve conflicts from many instruction sources.
2604.09443
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.