Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
LAAF: A Layered Accountability Architecture Framework for LLM Applications
Prachi Chaturvedi, Shahnawaz Ahmad, Ehsan Nowroozi +5
Large Language Models (LLMs) operate in hospitals, courtrooms, banks, and public service desks, where fluent, confident outputs are treated as authoritative even when ungrounded or…
cs.AI2026
Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement
Pierre Dantas, Lucas Cordeiro, Ehsan Nowroozi +2
Large Language Model (LLM) agents take irreversible real-world actions, yet no system gives formally grounded, task-level safety guarantees for their plans. In a PRISMA 2020 system…