# Large Language Models Meet Knowledge Graphs to Answer Factoid Questions

arXiv: https://arxiv.org/abs/2310.02166 · HTML: https://mlsanity.com/paper/2310.02166/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 12 of 12)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions](https://mlsanity.com/paper/2105.11644/) (2021)
- [Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering](https://mlsanity.com/paper/2210.01613/) (2022)
- [Multilingual Autoregressive Entity Linking](https://mlsanity.com/paper/2103.12528/) (2021)
- [KBQA: Learning Question Answering over QA Corpora and Knowledge Bases](https://mlsanity.com/paper/1903.02419/) (2019)
- [End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs](https://mlsanity.com/paper/2109.05817/) (2021)

## Built on by (most cited first, 11 of 11)

- [Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering](https://mlsanity.com/paper/2404.14741/) (2024)
- [Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval](https://mlsanity.com/paper/2405.06545/) (2024)
- [Entity Retrieval for Answering Entity-Centric Questions](https://mlsanity.com/paper/2408.02795/) (2024)
- [Personalized Graph-Based Retrieval for Large Language Models](https://mlsanity.com/paper/2501.02157/) (2025)
- [LLM-Independent Adaptive RAG: Let the Question Speak for Itself](https://mlsanity.com/paper/2505.04253/) (2025)
- [Large Language Models for Knowledge Graph Embedding: A Survey](https://mlsanity.com/paper/2501.07766/) (2025)
- [Pyramid-Driven Alignment: Pyramid Principle Guided Integration of Large Language Models and Knowledge Graphs](https://mlsanity.com/paper/2410.12298/) (2024)
- [An Entity Linking Agent for Question Answering](https://mlsanity.com/paper/2508.03865/) (2025)
- [BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment](https://mlsanity.com/paper/2509.07588/) (2025)
- [Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization](https://mlsanity.com/paper/2511.11946/) (2025)
- [MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models](https://mlsanity.com/paper/2605.15589/) (2026)

## Abstract (arXiv)

Recently, it has been shown that the incorporation of structured knowledge into Large Language Models significantly improves the results for a variety of NLP tasks. In this paper, we propose a method for exploring pre-trained Text-to-Text Language Models enriched with additional information from Knowledge Graphs for answering factoid questions. More specifically, we propose an algorithm for subgraphs extraction from a Knowledge Graph based on question entities and answer candidates. Then, we procure easily interpreted information with Transformer-based models through the linearization of the extracted subgraphs. Final re-ranking of the answer candidates with the extracted information boosts Hits@1 scores of the pre-trained text-to-text language models by 4-6%.