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

• URL: http://arxiv.org/abs/2608.29249v2
• Date: Tue, 01 Sep 2026 03:34:21 GMT
• Title: Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge
• Abstract summary: We present a semi-automated soundness assessment workflow for validating structured recipe data extracted and augmented by Large Language Models (LLMs)<n>Although evaluated on Indian recipes, the proposed methods are applicable to broader multilingual and multicultural culinary domains.
• Score: 2.334669361092524
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• ReGraph: Learning to Generate Recipe Graphs from Food Images [70.27418607642029]
  We present ReGraph, a large-scale recipe graph dataset that represents ingredients, cooking actions, and tools as entities.<n>We propose Recipe Graph Learning (RGL), a two-stage framework that enables LMMs to generate a plausible fine-grained cooking workflow from a food image.
  arXiv  Detail & Related papers  (2026-08-07T07:51:08Z)
• CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation [10.751176062286321]
  Accurate nutrient estimation from unstructured recipe text is an important yet challenging problem in dietary monitoring.<n>We evaluate models spanning a wide range of representational capacity, from lexical matching methods to deep semantic encoders.<n>Our results reveal a clear trade-off between predictive accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2026-04-28T15:41:01Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Enhancing Action and Ingredient Modeling for Semantically Grounded Recipe Generation [69.90401008542368]
  We propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation.<n> Experiments on Recipe1M show state-of-the-art performance and markedly improved semantic fidelity.
  arXiv  Detail & Related papers  (2026-01-26T10:06:18Z)
• A Highly Clean Recipe Dataset with Ingredient States Annotation for State Probing Task [25.030784769780368]
  We propose a new task and dataset for evaluating how well language models can recognize intermediate ingredient states during cooking procedures.<n>We first construct a new Japanese recipe dataset with clear and accurate annotations of ingredient state changes.<n>Using this dataset, we design three novel tasks to evaluate whether LLMs can track ingredient state transitions and identify ingredients present at intermediate steps.
  arXiv  Detail & Related papers  (2025-07-23T05:56:20Z)
• KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models [17.705244174235045]
  Recent advances in large language models (LLMs) and the abundance of food data have resulted in studies to improve food understanding.<n>We introduce KERL, a unified system that leverages food KGs and LLMs to provide personalized food recommendations.<n>We show that our proposed KG-augmented LLM significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-05-20T17:19:57Z)
• MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model [54.14155564592936]
  We propose a Mixture of Rule Experts guided by a Large Language Model (MoRE-LLM)<n>MoRE-LLM steers the discovery of local rule-based surrogates during training and their utilization for the classification task.<n>LLM is responsible for enhancing the domain knowledge alignment of the rules by correcting and contextualizing them.
  arXiv  Detail & Related papers  (2025-03-26T11:09:21Z)
• Retrieval Augmented Recipe Generation [96.43285670458803]
  We propose a retrieval augmented large multimodal model for recipe generation.<n>It retrieves recipes semantically related to the image from an existing datastore as a supplement.<n>It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation.
  arXiv  Detail & Related papers  (2024-11-13T15:58:50Z)
• LLaVA-Chef: A Multi-modal Generative Model for Food Recipes [17.705244174235045]
  Large language models (LLMs) have paved the way for Natural Language Processing approaches to delve deeper into food-related tasks. This work proposes LLaVA-Chef, a novel model trained on a curated dataset of diverse recipe prompts. A detailed qualitative analysis reveals that LLaVA-Chef generates more detailed recipes with precise ingredient mentions.
  arXiv  Detail & Related papers  (2024-08-29T20:20:49Z)
• FIRE: Food Image to REcipe generation [10.45344523054623]
  Food computing aims to develop end-to-end intelligent systems capable of autonomously producing recipe information for a food image. This paper proposes FIRE, a novel methodology tailored to recipe generation in the food computing domain. We showcase two practical applications that can benefit from integrating FIRE with large language model prompting.
  arXiv  Detail & Related papers  (2023-08-28T08:14:20Z)
• Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario [60.20197771545983]
  We design the counterfactual recipe generation task, which asks models to modify a base recipe according to the change of an ingredient. We collect a large-scale recipe dataset in Chinese for models to learn culinary knowledge. Results show that existing models have difficulties in modifying the ingredients while preserving the original text style, and often miss actions that need to be adjusted.
  arXiv  Detail & Related papers  (2022-10-20T17:21:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.