2 citations · 4 across the 21 of their papers we have counts for
9 papers · 1 filter
Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks
Bart Custers, Koorosh Aslansefat
This paper investigates how multi-agent systems (MAS)-based on large language models (LLMs) can support actuarial risk modelling, with a particular focus on uncertainty quantificat…
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…
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…
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…
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…
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…