HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering
Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks often provide response-level labels, with limited support for identifying the exact erroneous content, explaining why it is incorrect, or selecting the correct factual answer. We introduce \textsc{HalluTruthQA}, a fine-grained benchmark for hallucination evaluation in Arabic question answering. The benchmark contains 2,400 expert-curated examples across four knowledge-intensive domains: Islamic knowledge, history, scien
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%jeinlee1991/chinese-llm-benchmark →
“Fuzzy title match (0.73): “HalluTruthQA: A Fine-Grained Benchmark for Hallucination Det” ≈ “jeinlee1991/chinese-llm-benchmark””
- LinkedLinked via arxiv author · 85%Abdessalam Bouchekif →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”
- LinkedLinked via arxiv author · 85%Mohammed-En-Nadhir Zighem →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”
- LinkedLinked via arxiv author · 85%Salah Eddine Bekhouche →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”
- LinkedLinked via arxiv author · 85%Hichem Telli →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”
- LinkedLinked via arxiv author · 85%Somaya Eltanbouly →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”
- LinkedLinked via arxiv author · 85%Shahd Gaben →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”
- LinkedLinked via arxiv author · 85%Heba Sbahi →
“HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Ans”