Stefano Rini

The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA

This work isolates SLM graph reasoning from navigation and traceability capability by employing the THESEUS navigation and traceability framework and using frozen, off-the-shelf SLMs as local action policies, and results motivate evaluating SLM graph reasoning beyond endpoint accuracy alone.

Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation

This work re-frame multi-hop KGQA as a question-conditioned graph navigation problem, and refers to this formulation as THESEUS - Traceable Hop-wise Evidence SEarch in a Unified Semantics, advancing KGQA research toward systems where traceability is fundamental.

GCFed: Exploiting Gradient Correlation for Client Selection and Rate Allocation in Federated Learning