Search papers, labs, and topics across Lattice.
4
0
4
8
Madhhab-aware filtering can more than double retrieval accuracy for school-specific fiqh questions, revealing a crucial dimension in Islamic jurisprudence retrieval.
LLMs struggle with the complexities of Islamic scholarship, and the newly introduced ISTB reveals significant gaps in their performance across different levels of scholarly demand.
HalluTruthQA-4K reveals that over 40% of Arabic model-generated responses contain hallucinations, with detailed annotations that pinpoint specific errors and their explanations.
No single Arabic LLM can master hallucination detection, localization, and explanation, revealing critical gaps in current models' capabilities.
