Metraipolis › archive › dc_6fcfeb0acf8f
Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali — arXiv:2610.40996
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40996
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T07:41:56.209Z
- SHA-256 of the archived text
eeb82112296ba15e92e3946b05b2a3a2b852fc7f7f7a85b0230d2884af23e465- Stable URL of this page
https://metraipolis.com/documento/dc_6fcfeb0acf8f
How to cite
Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali — arXiv:2610.40996 — arXiv (en), https://arxiv.org/abs/2610.40996 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6fcfeb0acf8f (Metraipolis archive dc_6fcfeb0acf8f, sha256 eeb82112296ba15e92e3946b05b2a3a2b852fc7f7f7a85b0230d2884af23e465)
BibTeX
@misc{dc6fcfeb0acf8f,
title = {Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali — arXiv:2610.40996},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40996},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6fcfeb0acf8f; sha256 eeb82112296ba15e92e3946b05b2a3a2b852fc7f7f7a85b0230d2884af23e465},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40996. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When a language model invents a Qur'anic verse or hadith, it gives false authority to text that readers may treat as sacred. Existing Islamic hallucination benchmarks are largely Arabic and often closed-ended, while Bengali resources mainly study general-domain hallucination or factual knowledge. We introduce BILAL-BENCH, a 240-question expert-verified benchmark for open-ended Islamic-source fabrication in Bengali. It covers Qur'anic attribution, hadith, fiqh, contemporary issues, and adversarial false-premise prompts, and uses a two-axis rubric that separates source errors from assertiveness. We evaluate seven open-weight models from 1B to 120B on 1,680 double-annotated responses. Six of the seven models confidently fabricate on 79.3-95.3% of source-production questions, with no monotonic improvement from scale. Hadith provenance is the weakest category across models: only two of 315 responses are correct and correctly sourced. The two 8B BanglaLLaMA variants have similar confident-fabrication rates but different error profiles. Models vary far more in whether they withhold a claim they cannot support than in source accuracy: appropriate abstention or false-premise correction ranges from 6 to 46 responses across the benchmark, and does not track parameter count. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.40996 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-02T07:37:15.428Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).