A retrieval-augmented model can match a document without relying on it. Controlled knowledge conflicts make source choice observable and let us ask a second question that prediction alone cannot answer: which internal-state properties define useful intervention directions? We study paired hidden-state changes with Late...
Zhen-Qiang Yu, Wen-Peng Xing, Yun-Zhao Wei et al.· 0 citations
Budgeted Flat Reconstruction (BFR), which builds sufficient sets over a fixed flat memory store in two stages, and outperforms same-store adaptations of recent agent-memory systems in both answer quality and evidence coverage.
Yufeng Li, Shu-Xin Li, Zhenhua Xu et al.· 1 citation
This survey synthesizes 312 papers and first-party reports on text-based reasoning hallucinations around three questions: what evidence is observable, what study designs establish, and which corrective actions the evidence supports.
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 changes the next action. We study this gap through counterfactual role probes, component-wise activation patching, and separate interventions on...
Zhen-Qiang Yu, Wen-Peng Xing, Xing-Xing Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
