3 papers
cs.CL2026
IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources
Arash Ghafouri, Mahdi Firouzmandi, Hossein Saberi +1
Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classifi…
cs.IR2025
A Method for Multi-Hop Question Answering on Persian Knowledge Graph
Arash Ghafouri, Mahdi Firouzmandi, Hasan Naderi
Question answering systems are the latest evolution in information retrieval technology, designed to accept complex queries in natural language and provide accurate answers using b…
cs.CL2025
Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks
Iman Barati, Arash Ghafouri, Behrouz Minaei-Bidgoli
Multi-hop question answering requires a system to identify and integrate evidence distributed across documents, yet large language models remain vulnerable to irrelevant context. W…