The U.S. Consumer Financial Protection Bureau plans to propose in the coming days narrowing a key part of civil-rights era fair-lending regulations as Republican President Donald Trump's administratio...

ProPublica needs your help to track how the upheaval of public education is affecting schools and colleges in your community. Take a few minutes to join our source network and help guide our coverage.

The updated COVID-19 vaccines targeting the LP.8.1 variant have been approved by the FDA. But they may be a lot harder to get this year. Here's what you can do.

The annual awards are a celebration of weird but thought-provoking science.

Scientific societies, journals, editors and researchers are pushing back against mean-spirited peer reviews.

More sun might improve your heart and immune system. Just don’t get sunburnt

Taking vitamin D2 supplements seems to reduce levels of vitamin D3 in our body

Psilocybin appears to alter brain networks linked to repetitive negative thoughts, which may explain how the drug helps to treat some mental health conditions

The addictive anthem by the fictional girl group HUNTR/X just hit #1 on the Billboard Hot 100. The last one to do it was Destiny's Child.

Background: Traditional Chinese Medicine (TCM) emphasizes the concept of medicine food homology (MFH), integrating dietary therapy into #healthcare. However, applying MFH often requires extensive expert knowledge and manual interpretation, creating challenges for automating MFH-based dietary recommendations. While large language models (LLMs) show potential in #healthcare decision support, they often generate inaccurate or misleading information when involving knowledge in specific domains, such as TCM. Retrieval-augmented generation (RAG) addresses this by integrating external knowledge, but it struggles to model the inherent heterogeneity and uncertainty within TCM knowledge. Integrating uncertain knowledge graphs (UKGs) with LLMs offers a promising solution, as it not only provides a structured yet flexible representation of TCM's individualized principles but also enhances LLMs' ability to generate more accurate MFH-based dietary recommendations. Objective: This study introduces Yaoshi-RAG, a framework that leverages a UKG to enhance LLMs' capabilities in generating accurate and personalized MFH dietary recommendations based on TCM principles. Methods: The proposed framework began by constructing a comprehensive MFH knowledge graph (KG) through LLM-driven Open Information Extraction, which extracted structured data from multiple sources. It then employed UKG reasoning to complete missing triples and measured the confidence of the extracted triples. When processing user queries, query entities were identified and linked to the MFH KG, enabling retrieval of appropriate reasoning paths. These reasoning paths were then ranked based on triple confidence scores and entity importance to enhance accuracy. Finally, the retrieved knowledge was integrated through prompt engineering, enabling the LLM to generate personalized dietary recommendations that aligned with both individual user requirements and established TCM principles. The framework underwent validation through both automated metrics and human evaluation. Results: The constructed MFH KG comprised 24,984 entities, 22 relations, and 29,292 triples. Integration of this KG significantly enhanced LLM performance across all evaluation metrics, yielding an average increase of 14.5% in Hits@1 and 8.7% in F1-score, respectively. Among evaluated base LLMs, DeepSeek-R1 demonstrated superior performance, achieving 84.2% in Hits@1 and 71.5% in F1-score, respectively. Human evaluation corroborated these quantitative findings, confirming that Yaoshi-RAG consistently outperformed baseline models across all assessed quality dimensions. Conclusions: This study presents Yaoshi-RAG, a new framework that enhances LLMs' capabilities in generating MFH dietary recommendations through the knowledge retrieved from a UKG. By constructing a comprehensive MFH knowledge representation, our framework effectively extracts and utilizes TCM principles. Experimental results demonstrate the effectiveness of our framework in synthesizing traditional wisdom with advanced language models, facilitating personalized dietary recommendations that address individual #health conditions while providing evidence-based explanations grounded in TCM principles.