Metraipolis › archive › dc_83a33bdaa679

Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge — arXiv:2608.29249

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29249
License (as archived)
CC0-1.0
Archived
2026-10-17T07:44:10.330Z
SHA-256 of the archived text
7688cf3ea9a10e7d38617ce3dda76cd9ed6da6801e9d0bf3fb325eecdaea493d
Stable URL of this page
https://metraipolis.com/documento/dc_83a33bdaa679

How to cite

Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge — arXiv:2608.29249 — arXiv (en), https://arxiv.org/abs/2608.29249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83a33bdaa679 (Metraipolis archive dc_83a33bdaa679, sha256 7688cf3ea9a10e7d38617ce3dda76cd9ed6da6801e9d0bf3fb325eecdaea493d)
BibTeX
@misc{dc83a33bdaa679,
  title = {Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge — arXiv:2608.29249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83a33bdaa679; sha256 7688cf3ea9a10e7d38617ce3dda76cd9ed6da6801e9d0bf3fb325eecdaea493d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The online culinary ecosystem is increasingly populated by recipe content generated, modified, or summarized by Large Language Models (LLMs). While often plausible, such outputs may contain hallucinated ingredients, misrepresented quantities, or culturally implausible combinations, limiting their suitability for downstream applications and knowledge graph construction. In this paper, we present a semi-automated soundness assessment workflow for validating structured recipe data extracted and augmented by LLMs from informal culinary sources. Developed as part of FKG(.in), a knowledge graph of Indian food, the pipeline identifies and addresses common failure modes, including structural inconsistencies, semantic and logical incoherence, and deviations from the source text, through a multi-stage process combining formal grammars, vocabulary-based checks, statistical heuristics, Set Transformer-based coherence modeling, and retrieval-based verification. Although evaluated on Indian recipes, the proposed methods are applicable to broader multilingual and multicultural culinary domains. We provide a practical, auditable, and application-agnostic framework for validating LLM-augmented recipe data, thereby strengthening the foundations of machine-readable food knowledge infrastructures in the era of LLM-generated content.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.29249 — 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 2026-10-17T07:28:26.529Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).