{"data":{"id":"e89441d4-902b-41eb-b053-a05d6d1173de","title":"Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali","summary":"BILAL-BENCH is a 240-question, expert-verified benchmark for open-ended Islamic-source fabrication in Bengali, covering Qur'anic attribution, hadith, fiqh, contemporary issues and false-premise prompts. Evaluating seven open-weight models from 1B to 120B on 1,680 double-annotated responses, six of seven confidently fabricated on 79.3-95.3% of source-production questions, with no monotonic improvement from scale. Hadith provenance was the weakest category, with only two of 315 responses correct and correctly sourced.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.40996v1","publishedAt":"2026-10-29T21:25:31.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["BanglaLLaMA"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-29T21:25:31.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}