# LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking

arXiv: https://arxiv.org/abs/2407.04020 · HTML: https://mlsanity.com/paper/2407.04020/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 4 Jul 2024.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [Zero-Shot Entity Linking by Reading Entity Descriptions](https://mlsanity.com/paper/1906.07348/) (2019)
- [Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning](https://mlsanity.com/paper/2206.09363/) (2022)
- [ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking](https://mlsanity.com/paper/2207.04108/) (2022)
- [Improving Entity Linking by Modeling Latent Relations between Mentions](https://mlsanity.com/paper/1804.10637/) (2018)
- [Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators](https://mlsanity.com/paper/2310.07289/) (2023)
- [DeepType: Multilingual Entity Linking by Neural Type System Evolution](https://mlsanity.com/paper/1802.01021/) (2018)
- [When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks](https://mlsanity.com/paper/2311.08993/) (2023)
- [Fine-Grained Entity Typing for Domain Independent Entity Linking](https://mlsanity.com/paper/1909.05780/) (2019)
- [Instructed Language Models with Retrievers Are Powerful Entity Linkers](https://mlsanity.com/paper/2311.03250/) (2023)
- [Improving Short Text Classification With Augmented Data Using GPT-3](https://mlsanity.com/paper/2205.10981/) (2022)
- [KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding](https://mlsanity.com/paper/2307.03115/) (2023)
- [Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations](https://mlsanity.com/paper/2204.11241/) (2022)
- [A Unified Approach to Entity-Centric Context Tracking in Social Conversations](https://mlsanity.com/paper/2201.12409/) (2022)
- [Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata](https://mlsanity.com/paper/2305.14202/) (2023)

## Built on by (most cited first, 19 of 19)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [Contextual Augmentation for Entity Linking using Large Language Models](https://mlsanity.com/paper/2510.18888/) (2025)
- [Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning](https://mlsanity.com/paper/2510.20098/) (2025)
- [DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking](https://mlsanity.com/paper/2508.15876/) (2025)
- [Can an LLM Induce a Graph? Investigating Memory Drift and Context Length](https://mlsanity.com/paper/2510.03611/) (2025)
- [Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoning](https://mlsanity.com/paper/2409.15113/) (2024)
- [Evaluation of LLMs on Long-tail Entity Linking in Historical Documents](https://mlsanity.com/paper/2505.03473/) (2025)
- [IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences](https://mlsanity.com/paper/2605.06142/) (2026)
- [SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking](https://mlsanity.com/paper/2601.19667/) (2026)
- [REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking](https://mlsanity.com/paper/2510.11592/) (2025)
- [DELICATE: Diachronic Entity LInking using Classes And Temporal Evidence](https://mlsanity.com/paper/2511.10404/) (2025)
- [LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking](https://mlsanity.com/paper/2605.13451/) (2026)
- [BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision](https://mlsanity.com/paper/2605.27380/) (2026)
- [Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection](https://mlsanity.com/paper/2608.27470/) (2026)
- [Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking](https://mlsanity.com/paper/2609.00228/) (2026)
- [Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking](https://mlsanity.com/paper/2609.07379/) (2026)
- [Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking](https://mlsanity.com/paper/2609.10745/) (2026)

## Abstract (arXiv)

Specialized entity linking (EL) models are well-trained at mapping mentions to unique knowledge base (KB) entities according to a given context. However, specialized EL models struggle to disambiguate long-tail entities due to their limited training data. Meanwhile, extensively pre-trained large language models (LLMs) possess broader knowledge of uncommon entities. Yet, with a lack of specialized EL training, LLMs frequently fail to generate accurate KB entity names, limiting their standalone effectiveness in EL. With the observation that LLMs are more adept at context generation instead of EL execution, we introduce LLM-Augmented Entity Linking (LLMAEL), the first framework to enhance specialized EL models with LLM data augmentation. LLMAEL leverages off-the-shelf, tuning-free LLMs as context augmenters, generating entity descriptions to serve as additional input for specialized EL models. Experiments show that LLMAEL sets new state-of-the-art results across 6 widely adopted EL benchmarks: compared to prior methods that integrate tuning-free LLMs into EL, LLMAEL achieves an absolute 8.9% gain in EL accuracy. We release our code and datasets.