Eric Wong
2 papers · Latest:
Artificial Intelligence
Detecting Safety Violations Across Many Agent Traces
Meerkat uses clustering and agentic search to detect rare, complex safety violations across many agent traces, outperforming existing methods.
2604.11806
Natural Language ProcessingDetecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
This paper measures and corrects citation hallucinations in LLMs and research agents, finding 3-13% of URLs are fabricated.
2604.03173
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.