works on

From the 2 of 22 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.AIShow all

7 papers · 1 filter

cs.AI2026

Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks

Bart Custers, Koorosh Aslansefat

The paper presents a framework for monitoring runtime uncertainty in large‑language‑model based multi‑agent systems by converting token‑level log‑probabilities into calibrated conf…

cs.AI2026

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI

Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani +3

Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce…

cs.AI2026

Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering

Louis Donaldson, Connor Walker, Koorosh Aslansefat +1

Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines may fail. This paper presents…

cs.AI2026

Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Framework

Zeinab Dehghani, Rameez Raja Kureshi, Koorosh Aslansefat +6

Artificial intelligence (AI) is increasingly being explored in health and social care to reduce administrative workload and allow staff to spend more time on patient care. This pap…

cs.AI2025

RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs

Connor Walker, Koorosh Aslansefat, Mohammad Naveed Akram +1

Accuracy and safety are paramount in Offshore Wind (OSW) maintenance, yet conventional Large Language Models (LLMs) often fail when confronted with highly specialised or unexpected…

cs.AI2025

Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE

Zahra Zehtabi Sabeti Moghaddam, Zeinab Dehghani, Maneeha Rani +4

Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive d…