# Quantifying Hidden Salt for Precision Healthcare: Sodium Assessment via Joint-Factor Retrieval and Chain-of-Thought Inference

arXiv: https://arxiv.org/abs/2609.22171 · HTML: https://mlsanity.com/paper/2609.22171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [A Survey on Food Computing](https://mlsanity.com/paper/1808.07202/) (2018)
- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)
- [NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning](https://mlsanity.com/paper/2412.15547/) (2024)
- [SHARE: a System for Hierarchical Assistive Recipe Editing](https://mlsanity.com/paper/2105.08185/) (2021)
- [LLaVA-Chef: A Multi-modal Generative Model for Food Recipes](https://mlsanity.com/paper/2408.16889/) (2024)
- [ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation](https://mlsanity.com/paper/2409.12010/) (2024)
- [UMDFood: Vision-language models boost food composition compilation](https://mlsanity.com/paper/2306.01747/) (2023)
- [KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models](https://mlsanity.com/paper/2505.14629/) (2025)
- [When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition](https://mlsanity.com/paper/2511.20652/) (2025)
- [From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent](https://mlsanity.com/paper/2608.13581/) (2026)

## Abstract (arXiv)

Precision healthcare, particularly for conditions like hypertension and cardiovascular disease, necessitates monitoring of dietary sodium intake. However, tracking this is hindered by the prevalence of hidden salt in cooking, such as sodium in soy sauce and ketchup. While recipes offer a valuable data source for dietary analysis, sodium-rich seasonings are frequently omitted or described ambiguously in instructions. To solve this issue, we propose SALT, a Sodium Assessing & Level Tracking framework adopting an RAG framework to assess sodium content in recipes. Our framework first introduces a Joint-Factor Embedding Retrieval module to locate similar recipes with specified sodium content for addressing the lack of contextual references. These retrieved samples provide contexts for subsequent inference. Then we design a structured 4-hop Chain-of-Thought inference module to refine the vague estimation from language models through a multi-step sodium estimation. To facilitate our study, we further construct a recipe dataset SALT54k with 54,151 entries labeled with sodium quantities across 11 common seasonings. Results on SALT54k demonstrate that our method achieves state-of-the-art performance in sodium estimation. Additional real-world validations confirm the effectiveness of our method, demonstrating its potential as a practical solution for AI-assisted precision healthcare.