3 papers
cs.AI2026
Readable Before Actionable: Causal Tracing of Indirect Prompt Injection
Zhe Yu, Wenpeng Xing, Xingxing Yang +1
Indirect prompt injection causes LLM agents to follow commands embedded in external data. A probe may distinguish instructions from data without identifying a state edit that chang…
cs.AI2026
LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
Zhe Yu, Wenpeng Xing, Meng Han
Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually suppo…
cs.AI2026
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
Zhe Yu, Wenpeng Xing, Meng Han
Hallucinations in medical large language models (LLMs) remain a safety-critical issue, particularly when available evidence is insufficient or conflicting. We study this problem in…