Category: Engineering

Traditional RAG systems struggle to capture relationships and cross-references between different sources unless explicitly mentioned. This challenge is common in real-world scenarios, where information is often distributed and interlinked, making graphs a more effective representation. Our work provides a technical contribution through a comparative evaluation of retrieval strategies within GraphRAG, focusing on context relevance rather than abstract metrics. We aim to offer practitioners actionable insights into the retrieval component of the GraphRAG pipeline.

We proposed a feature unlearning technique to reduce cancer-type bias, which improved segmentation accuracy while promoting fairness across sub-groups, even with limited data.