Papers with graph-based RAGs

2 papers
FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: FinGEAR provides a retrieval framework tailored to financial documents . standard retrieval-augmented generation models underuse financial disclosures .
Approach: FinGEAR combines a finance lexicon for Item-level guidance and hierarchical indices for within-Item search.
Outcome: FinGEAR improves accuracy and accuracy on 10-Ks with a FinQA dataset.
MS-RAG: Simple and Effective Multi-Semantic Retrieval-Augmented Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for large language models suffer from poor indexing and inference speed . graph-based RAGs heavily rely on LLM for retrieval thus inference slow .
Approach: They propose retrieval-augmented generation (RAG) which integrates knowledge with dense vectors to build a multi-semantic RAG.
Outcome: The proposed method achieves state-of-the-art performance with faster inference speed compared to existing methods .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations