mlsanityData to 7 Oct 2026

LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation

arXiv 2601.05192 ↗First posted 8 Jan 2026cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Entity linking (mapping ambiguous mentions in text to entities in a knowledge base) is a foundational step in tasks such as knowledge graph construction, question-answering, and information extraction. Our method, LELA, is a modular coarse-to-fine approach that leverages the capabilities of large language models (LLMs), and works with different target domains, knowledge bases and LLMs, without any fine-tuning phase. Our experiments across various entity linking settings show that LELA is highly competitive with fine-tuned approaches, and substantially outperforms the non-fine-tuned ones.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 52 of its 78 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

52 of 78 references.

References · 52

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  9. 2016Sequence-Level Knowledge Distillationcited by 761
  10. 2024The Faiss librarycited by 370
  11. 2020Autoregressive Entity Retrievalcited by 333
  12. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
38 more
  1. 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
  2. 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMscited by 115
  3. 2022ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linkingcited by 74
  4. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 58
  5. 2020Machine Knowledge: Creation and Curation of Comprehensive Knowledge Basescited by 55
  6. 2021Multilingual Autoregressive Entity Linkingcited by 50
  7. 2024TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategycited by 47
  8. 2020Neural Entity Linking: A Survey of Models Based on Deep Learningcited by 46
  9. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankerscited by 42
  10. 2025ReasonRank: Empowering Passage Ranking with Strong Reasoning Abilitycited by 39
  11. 2025LongCodeZip: Compress Long Context for Code Language Modelscited by 38
  12. 2023YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomycited by 37
  13. 2019Fine-Grained Entity Typing for Domain Independent Entity Linkingcited by 36
  14. 2024Match, Compare, or Select? An Investigation of Large Language Models for Entity Matchingcited by 32
  15. 2017Named Entity Disambiguation for Noisy Textcited by 24
  16. 2025jina-reranker-v3: Last but Not Late Interaction for Listwise Document Rerankingcited by 23
  17. 2021Highly Parallel Autoregressive Entity Linking with Discriminative Correctioncited by 21
  18. 2024LLMAEL: Large Language Models are Good Context Augmenters for Entity Linkingcited by 19
  19. 2020Empirical Evaluation of Pretraining Strategies for Supervised Entity Linkingcited by 17
  20. 2022Design of Negative Sampling Strategies for Distantly Supervised Skill Extractioncited by 16
  21. 2020Zero-shot Entity Linking with Efficient Long Range Sequence Modelingcited by 13
  22. 2023Generative Multimodal Entity Linkingcited by 11
  23. 2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillationcited by 11
  24. 2019Global Entity Disambiguation with BERTcited by 10
  25. 2025CoRanking: Collaborative Ranking with Small and Large Ranking Agentscited by 10
  26. 2024OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Promptingcited by 9
  27. 2024Entity Linking in the Job Market Domaincited by 7
  28. 2025Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?cited by 7
  29. 2022Effective Few-Shot Named Entity Linking by Meta-Learningcited by 6
  30. 2023A Read-and-Select Framework for Zero-shot Entity Linkingcited by 6
  31. 2023GLADIS: A General and Large Acronym Disambiguation Benchmarkcited by 5
  32. 2025Evaluating Design Decisions for Dual Encoder-based Entity Disambiguationcited by 5
  33. 2025zELO: ELO-inspired Training Method for Rerankers and Embedding Modelscited by 5
  34. 2025Contextual Augmentation for Entity Linking using Large Language Modelscited by 5
  35. 2022ELEVANT: A Fully Automatic Fine-Grained Entity Linking Evaluation and Analysis Toolcited by 4
  36. 2024Entity Disambiguation via Fusion Entity Decodingcited by 4
  37. 2024UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Modelscited by 4
  38. 2025Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoningcited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026BeLink: Biomedical Entity Linking Meets Generative Re-Rankingcited by 1
  2. 2026LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptationcited by 1
  3. 2026KARLA: Knowledge-base Augmented Retrieval for Language Modelscited by 0
  4. 2026GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Basecited by 0
  5. 2026Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selectioncited by 0
  6. 2026Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linkingcited by 0