Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach

arXiv cs.CL Papers
scientific-ner large-language-models multi-task-learning type-driven information-extraction in-context-learning

Summary

This paper proposes TdSciNER, a type-driven multi-task learning approach that leverages LLMs to improve scientific named entity recognition by filtering entity types, adding an auxiliary typing task, and using a demonstration selection strategy. Experiments on three datasets show performance comparable to fully supervised models.

arXiv:2608.08636v1 Announce Type: new Abstract: Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recognition and classification by LLMs. However, when too many candidate entity types are provided in the prompt, LLMs struggle to accurately recognize and label entities in scientific texts, where entity types are more complex than in general domains. To address this challenge, we propose TdSciNER, a type-driven approach that effectively leverages entity type information to enhance SciNER performance. In TdSciNER, we first design an entity type filter model to identify the most likely entity types present in a given sentence. Subsequently, we introduce an auxiliary multi-class entity typing task within a multi-task learning framework alongside SciNER to obtain richer contextual representations. Then, we develop a novel demonstration selection strategy based on sentence similarity and entity type diversity to activate the in-context learning capabilities of LLMs, thereby improving entity recognition accuracy across diverse scientific domains. Experiments on three datasets demonstrate that our method achieves performance comparable to fully supervised models. Further analysis validates that each entity type-driven component in TdSciNER contributes to the improvement of SciNER performance. This work provides valuable insights for future advancements in SciNER and broader information extraction tasks in scientific text mining.
Original Article
View Cached Full Text

Cached at: 08/11/26, 08:09 AM 

# Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach
Source: [https://arxiv.org/abs/2608.08636](https://arxiv.org/abs/2608.08636)
[View PDF](https://arxiv.org/pdf/2608.08636)

> Abstract:Scientific named entity recognition \(SciNER\) plays a crucial role in information extraction and knowledge discovery from scientific texts\. Recently, large language models \(LLMs\) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort\. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recognition and classification by LLMs\. However, when too many candidate entity types are provided in the prompt, LLMs struggle to accurately recognize and label entities in scientific texts, where entity types are more complex than in general domains\. To address this challenge, we propose TdSciNER, a type\-driven approach that effectively leverages entity type information to enhance SciNER performance\. In TdSciNER, we first design an entity type filter model to identify the most likely entity types present in a given sentence\. Subsequently, we introduce an auxiliary multi\-class entity typing task within a multi\-task learning framework alongside SciNER to obtain richer contextual representations\. Then, we develop a novel demonstration selection strategy based on sentence similarity and entity type diversity to activate the in\-context learning capabilities of LLMs, thereby improving entity recognition accuracy across diverse scientific domains\. Experiments on three datasets demonstrate that our method achieves performance comparable to fully supervised models\. Further analysis validates that each entity type\-driven component in TdSciNER contributes to the improvement of SciNER performance\. This work provides valuable insights for future advancements in SciNER and broader information extraction tasks in scientific text mining\.

## Submission history

From: Chengzhi Zhang \[[view email](https://arxiv.org/show-email/3d57d48b/2608.08636)\] **\[v1\]**Sun, 9 Aug 2026 10:59:37 UTC \(5,239 KB\)

Similar Articles

Labeling Training Data for Entity Matching Using Large Language Models

arXiv cs.CL

This paper investigates using LLMs as teacher models to label training data for entity matching, showing that student models trained on machine-labeled data perform on par with those trained on manually labeled benchmarks, with significant cost and speed advantages.

From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models

arXiv cs.CL

The paper introduces a multi-layer taxonomy for large language models comprising 14 capability domains and 91 subskills, drawing from human cognitive science to organize LLM evaluation beyond isolated tasks. It demonstrates operational utility by mapping 15,934 papers across major AI conferences, revealing concentrated attention on language-semantic competence and reasoning while identifying underexplored domains.