Papers by Youness Moukafih

Copied to clipboard

Challenge:	Large language models (LLMs) have recently achieved impressive results on multiple-choice question answering (MCQA) despite advances in English, LLMs continue to underperform in Arabic due to gaps in data coverage, linguistic transfer, and evaluation design.
Approach:	They propose a method that jointly models the relevance of both the question and its candidate answers when selecting contextual passages.
Outcome:	The proposed approach outperforms standard RAG baselines and reranker baselines while remaining competitive with considerably larger models.