Metraipolis › archive › dc_a5da59dace68
LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text — arXiv:2609.06993
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06993
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:57:05.186Z
- SHA-256 of the archived text
ab1883eabd577f637bf5c396d8983b17de8d7eb0672567f386b407468e617c74- Stable URL of this page
https://metraipolis.com/documento/dc_a5da59dace68
How to cite
LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text — arXiv:2609.06993 — arXiv (en), https://arxiv.org/abs/2609.06993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5da59dace68 (Metraipolis archive dc_a5da59dace68, sha256 ab1883eabd577f637bf5c396d8983b17de8d7eb0672567f386b407468e617c74)
BibTeX
@misc{dca5da59dace68,
title = {LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text — arXiv:2609.06993},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06993},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5da59dace68; sha256 ab1883eabd577f637bf5c396d8983b17de8d7eb0672567f386b407468e617c74},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelines. Yet existing evaluations often conflate content quality with format adherence, leaving Markdown boundary failures under-measured. We introduce LatentMD, a benchmark and evaluation protocol for diagnosing CommonMark-level fence-boundary failures in LLM-generated Markdown. LatentMD separates content correctness from boundary correctness, enabling detection of outputs that are content-correct but boundary-broken. The benchmark contains 4,179 prompts and a CLI for scoring arbitrary model outputs. Across 9 LLMs and roughly 37,600 generations, we find that Markdown boundary failures are widespread: 38.0% of valid main-grid outputs are content-correct but boundary-broken, with substantial boundary breakage under unspecified prompts and in a small human-authored validation set. Ablations show that failures are driven primarily by same-family symmetric-delimiter collisions rather than nesting alone, are only partially mitigated by prompt hints, and generalize to Python triple-quote docstrings while JSON remains robust as an asymmetric-delimiter control. LatentMD provides a reproducible diagnostic target for parser-sensitive LLM evaluation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Software Engineering (cs.SE) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.06993 — 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 2026-10-16T12:30:25.299Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).