RiTeK: Medical Textual Knowledge Graph QA Benchmark

RiTeK is a benchmark for complex reasoning over medical Textual Knowledge Graphs (TKGs). It contains three medical graph QA subsets, including ADint, to evaluate retrieval systems and Large Language Models (LLMs). The dataset was created by ChenAI2015 and last updated on 2026-04-11.

Use Cases

• Benchmarking retrieval systems for medical knowledge graphs based on relational paths and textual descriptions.
• Evaluating LLM reasoning capabilities on realistic medical questions using textual knowledge graphs.
• Training models for complex multi-hop reasoning in the medical domain based on the benchmark structure.

Strengths

• Designed for complex reasoning tasks over medical textual knowledge graphs.
• Contains three distinct QA subsets, including ADint, with train/dev/test splits.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and sample data are unknown, which may limit suitability assessment.

Provenance

Source

huggingface, author ChenAI2015

Collection Method

Likely constructed as a benchmark for evaluating systems.

Time Range

null

Freshness

Last updated 2026-04-11 14:05:26; freshness should be verified.

Geography

null