# RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models

arXiv: https://arxiv.org/abs/2505.19128 · HTML: https://mlsanity.com/paper/2505.19128/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 25 May 2025.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023)
- [LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities](https://mlsanity.com/paper/2305.13168/) (2023)
- [CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors](https://mlsanity.com/paper/2305.05711/) (2023)
- [LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild](https://mlsanity.com/paper/2402.09997/) (2024)
- [PromptNER: Prompting For Named Entity Recognition](https://mlsanity.com/paper/2305.15444/) (2023)
- [Batched Low-Rank Adaptation of Foundation Models](https://mlsanity.com/paper/2312.05677/) (2023)
- [Label Supervised LLaMA Finetuning](https://mlsanity.com/paper/2310.01208/) (2023)
- [PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets](https://mlsanity.com/paper/2211.14838/) (2022)
- [DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition](https://mlsanity.com/paper/2305.03688/) (2023)
- [P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models](https://mlsanity.com/paper/2405.04960/) (2024)
- [DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition](https://mlsanity.com/paper/2409.11022/) (2024)

## Abstract (arXiv)

The rise of large language models has led to significant performance breakthroughs in named entity recognition (NER) for high-resource languages, yet there remains substantial room for improvement in low- and medium-resource languages. Existing multilingual NER methods face severe language interference during the multi-language adaptation process, manifested in feature conflicts between different languages and the competitive suppression of low-resource language features by high-resource languages. Although training a dedicated model for each language can mitigate such interference, it lacks scalability and incurs excessive computational costs in real-world applications. To address this issue, we propose RetrieveAll, a universal multilingual NER framework based on dynamic LoRA. The framework decouples task-specific features across languages and demonstrates efficient dynamic adaptability. Furthermore, we introduce a cross-granularity knowledge augmented method that fully exploits the intrinsic potential of the data without relying on external resources. By leveraging a hierarchical prompting mechanism to guide knowledge injection, this approach advances the paradigm from "prompt-guided inference" to "prompt-driven learning." Experimental results show that RetrieveAll outperforms existing baselines; on the PAN-X dataset, it achieves an average F1 improvement of 12.1 percent.