# Direct Fact Retrieval from Knowledge Graphs without Entity Linking

arXiv: https://arxiv.org/abs/2305.12416 · HTML: https://mlsanity.com/paper/2305.12416/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2023.

## Built on by (most cited first, 22 of 22)

- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey](https://mlsanity.com/paper/2504.10499/) (2025)
- [CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era](https://mlsanity.com/paper/2412.18702/) (2024)
- [EffiQA: Efficient Question-Answering with Strategic Multi-Model Collaboration on Knowledge Graphs](https://mlsanity.com/paper/2406.01238/) (2024)
- [Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering](https://mlsanity.com/paper/2403.02966/) (2024)
- [What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge](https://mlsanity.com/paper/2508.08344/) (2025)
- [R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL](https://mlsanity.com/paper/2311.01862/) (2023)
- [Unified Multimodal Interleaved Document Representation for Retrieval](https://mlsanity.com/paper/2410.02729/) (2024)
- [Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking](https://mlsanity.com/paper/2508.02435/) (2025)
- [KET-QA: A Dataset for Knowledge Enhanced Table Question Answering](https://mlsanity.com/paper/2405.08099/) (2024)
- [Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities](https://mlsanity.com/paper/2508.01290/) (2025)
- [RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs](https://mlsanity.com/paper/2510.01257/) (2025)
- [MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources](https://mlsanity.com/paper/2406.04670/) (2024)
- [Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering](https://mlsanity.com/paper/2511.04072/) (2025)
- [GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge](https://mlsanity.com/paper/2512.14766/) (2025)
- [SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval](https://mlsanity.com/paper/2412.15443/) (2024)
- [RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QA](https://mlsanity.com/paper/2512.15219/) (2025)
- [OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources](https://mlsanity.com/paper/2605.29250/) (2026)
- [Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)](https://mlsanity.com/paper/2606.05901/) (2026)
- [MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA](https://mlsanity.com/paper/2607.14561/) (2026)

## Abstract (arXiv)

There has been a surge of interest in utilizing Knowledge Graphs (KGs) for various natural language processing/understanding tasks. The conventional mechanism to retrieve facts in KGs usually involves three steps: entity span detection, entity disambiguation, and relation classification. However, this approach requires additional labels for training each of the three subcomponents in addition to pairs of input texts and facts, and also may accumulate errors propagated from failures in previous steps. To tackle these limitations, we propose a simple knowledge retrieval framework, which directly retrieves facts from the KGs given the input text based on their representational similarities, which we refer to as Direct Fact Retrieval (DiFaR). Specifically, we first embed all facts in KGs onto a dense embedding space by using a language model trained by only pairs of input texts and facts, and then provide the nearest facts in response to the input text. Since the fact, consisting of only two entities and one relation, has little context to encode, we propose to further refine ranks of top-k retrieved facts with a reranker that contextualizes the input text and the fact jointly. We validate our DiFaR framework on multiple fact retrieval tasks, showing that it significantly outperforms relevant baselines that use the three-step approach.