# Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge

arXiv: https://arxiv.org/abs/2608.29249 · HTML: https://mlsanity.com/paper/2608.29249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [ProoFVer: Natural Logic Theorem Proving for Fact Verification](https://mlsanity.com/paper/2108.11357/) (2021)
- [GERE: Generative Evidence Retrieval for Fact Verification](https://mlsanity.com/paper/2204.05511/) (2022)
- [HALoGEN: Fantastic LLM Hallucinations and Where to Find Them](https://mlsanity.com/paper/2501.08292/) (2025)
- [DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation](https://mlsanity.com/paper/2412.13175/) (2024)
- [NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions](https://mlsanity.com/paper/2407.12843/) (2024)
- [LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification](https://mlsanity.com/paper/2012.13577/) (2020)
- [From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification](https://mlsanity.com/paper/2310.11675/) (2023)
- [Revisiting text decomposition methods for NLI-based factuality scoring of summaries](https://mlsanity.com/paper/2211.16853/) (2022)
- [FoodSky: A Food-oriented Large Language Model that Passes the Chef and Dietetic Examination](https://mlsanity.com/paper/2406.10261/) (2024)
- [ProVe: A Pipeline for Automated Provenance Verification of Knowledge Graphs against Textual Sources](https://mlsanity.com/paper/2210.14846/) (2022)
- [Evaluating Large Language Models for Structured Science Summarization in the Open Research Knowledge Graph](https://mlsanity.com/paper/2405.02105/) (2024)
- [Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study](https://mlsanity.com/paper/2502.02028/) (2025)

## Abstract (arXiv)

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.