Metraipolis › archive › dc_c77d3217eecd
Where LLMs Fail with Visualization DSLs — arXiv:2610.01873
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01873
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T13:57:37.128Z
- SHA-256 of the archived text
d87641d53ed96d1398ce39697c56672d4fb58b72bab8dc65ace1ac0508b1407b- Stable URL of this page
https://metraipolis.com/documento/dc_c77d3217eecd
How to cite
Where LLMs Fail with Visualization DSLs — arXiv:2610.01873 — arXiv (en), https://arxiv.org/abs/2610.01873 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c77d3217eecd (Metraipolis archive dc_c77d3217eecd, sha256 d87641d53ed96d1398ce39697c56672d4fb58b72bab8dc65ace1ac0508b1407b)
BibTeX
@misc{dcc77d3217eecd,
title = {Where LLMs Fail with Visualization DSLs — arXiv:2610.01873},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01873},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c77d3217eecd; sha256 d87641d53ed96d1398ce39697c56672d4fb58b72bab8dc65ace1ac0508b1407b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01873. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As LLMs take up the role of authoring charts using visualization domain-specific languages (DSLs), the human constraints that shaped those languages may no longer apply, as what is easy for a person is not necessarily easy for a model. To understand how LLMs might work better with DSLs, we explore where and how they fail with current DSL designs. We evaluate 10 JSON-style visualization DSLs with 41 tasks across 3 LLMs, then assess the generated specifications with JSON and rendering checks, and qualitative coding of failed cases. Analyzing how this specification generation process fails, we identify four recurring failure patterns, link each to specific DSL features, and discuss design considerations for future DSL designs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.01873 — 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 2026-10-06T12:15:34.850Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).