Metraipolis › archive › dc_e3cfdd447585
BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models — arXiv:2608.27268
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27268
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:23:41.533Z
- SHA-256 of the archived text
e60e1a4f4b1aaae5ace726e80c51d848ea16991a2e2fd9d9543fe24373997e66- Stable URL of this page
https://metraipolis.com/documento/dc_e3cfdd447585
How to cite
BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models — arXiv:2608.27268 — arXiv (en), https://arxiv.org/abs/2608.27268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3cfdd447585 (Metraipolis archive dc_e3cfdd447585, sha256 e60e1a4f4b1aaae5ace726e80c51d848ea16991a2e2fd9d9543fe24373997e66)
BibTeX
@misc{dce3cfdd447585,
title = {BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models — arXiv:2608.27268},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27268},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3cfdd447585; sha256 e60e1a4f4b1aaae5ace726e80c51d848ea16991a2e2fd9d9543fe24373997e66},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Although Large language models (LLMs) mediate access to knowledge and computational assistance, their capabilities should benefit vulnerable groups in the same way. However, it is unclear whether existing AI systems are inclusive enough for blind and deafblind users to access the same functionality through Braille, whose indicators, contractions, and digital representations introduce distinct requirements for model comprehension. To this end, we introduce BrailleBench, a benchmark for evaluating LLMs in Braille comprehension from different Criteria. BrailleBench aligns 5,570 instances from five datasets, including mathematics, commonsense, and multi-hop question answering across English and Braille Grades 1 and 2. Different configurations are designed to understand whether the systems can comprehend Braille-authored content, express answers in Braille, and complete end-to-end Braille interaction. To ensure the quality and prevent evaluation bias, the benchmark is built through a deterministic, expert-reviewed pipeline via a self-created Braille Toolkit without using any data instances generated by LLMs. We evaluate six representative LLMs from various aspects. The results reveal a persistent gap between print-English capability and Braille accessibility. Braille understanding and expression are asymmetric, where Grade 2 is especially fragile on the input side compared to Grade 1, and fully Braille requests further reduce performance. The experimental observations provide valuable guidance for the development of future Braille AI systems. All related resources in BrailleBench are publicly available for future research. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2608.27268 — 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 2026-10-17T13:16:53.563Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).