Challenge: Existing work on how to effectively capture multi-document relationships remains an open question . Existing techniques to mitigate this problem include hierarchical summarization of semantically related chunks or integrating Knowledge Graphs (KGs).
Approach: They propose a method which constructs a local knowledge graph from retrieved documents . they use propositional claims to construct a knowledge graph and contextualize a small language model .
Outcome: The proposed method outperforms RAG on biomedical benchmarks and is generalizable and effective.

Similar Papers

Iterative Knowledge Graph Refinement and Integration for Medical Question Answering (2026.findings-acl)

Copied to clipboard

Challenge: Existing graph-based RAG methods heuristically retrieve and refine question-relevant subgraphs, potentially introducing redundant and noisy factual information that is difficult for LLMs to process.
Approach: They propose to integrate knowledge graphs (KGs) through retrieval-augmented generation methods to improve LLM reasoning by incorporating external trustworthy knowledge resources.
Outcome: The proposed framework achieves state-of-the-art against baseline competitors on three medical QA benchmark datasets.
Retrieval-based Question Answering with Passage Expansion Using a Knowledge Graph (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in dense neural retrievers and language models have hindered performance, especially for less common entities and facts.
Approach: They propose a multi-modal passage retrieval model that combines entity features and textual data to improve retrieval precision for less common entities.
Outcome: The proposed model improves retrieval precision on less common entities and facts on common benchmarks.
MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Existing RAG solutions for large language models are limited by context windows limiting their ability to process long-form, domain-specific content.
Approach: They propose a multimodal knowledge graph-based RAG that enables cross-modal reasoning . their method incorporates visual cues into the construction of knowledge graphs, retrieval phase, and answer generation process .
Outcome: Experimental results show that the proposed approach outperforms existing approaches on textual and multimodal benchmarks.
RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking (2026.findings-acl)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) integrates knowledge from tables with an external knowledge base to improve the answer relevance and accuracy.
Approach: They propose a table-corpora-aware RAG framework called T-RAG to integrate external knowledge into Large Language Models (LLMs) they then develop a multi-table question answering benchmark called MultiTableQA which spans 3 different task types, 57,193 tables, and 23,758 questions in total.
Outcome: The proposed framework achieves state-of-the-art accuracy, recall, and runtime performance, with improvements of up to 9.4%.
Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: GraphRAG framework is designed to enhance LLMs in generating evidence-based medical responses.
Approach: They propose a graph-based Retrieval-augmented generation framework to enhance LLMs in generating evidence-based medical responses.
Outcome: The proposed framework outperforms state-of-the-art models on 9 medical Q&A benchmarks, 2 health fact-checking datasets, and a long-form generation test set.
Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models have greatly advanced medical Question Answering (QA) however, the rapid evolution of medical knowledge and manual updating of domain-specific resources can undermine reliability of these systems.
Approach: AMG-RAG automates the construction and continuous updating of Medical Knowledge Graph (MKG) . afriq: rapid evolution of medical knowledge and manual updating can undermine reliability of LLMs .
Outcome: AMG-RAG achieves an F1 score of 74.1% on MEDQA and an accuracy of 66.34% on medMCQA.
Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision (2022.coling-1)

Copied to clipboard

Challenge: Current medical question answering systems have difficulty processing long, detailed and informally worded questions . a growing number of approaches attempt to enhance the processing of consumer health questions - or medical question understanding .
Approach: They propose a medical question understanding and answering system with knowledge grounding and semantic self-supervision that matches a user question with a trusted medical knowledge base and retrieves a fixed number of relevant sentences from the corresponding answer document.
Outcome: The proposed system retrieves more relevant answers while achieving 20 times faster.
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to knowledge graph question answering (KGQA) rely on Large Language Model (LLM) agents for graph traversal and retrieval.
Approach: They propose a framework that synergizes Large Language Models with specialized graph retrieval tools to enhance KGQA.
Outcome: The proposed framework outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs.
KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing to retrieve knowledge strictly necessary for answer generation.
Approach: They propose a retrieval-filtering-summarization pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information.
Outcome: The proposed pipeline surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.
KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods that address corpus-level context loss focus on query enrichment through structured relation representations.
Approach: They propose a framework for Contextual Query Retrieval that enriches queries with contextual representations derived from a corpus-centric KG.
Outcome: The proposed framework outperforms strong baselines on RAGBench and MultiHop-RAG datasets in terms of retrieval effectiveness.

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