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

• URL: http://arxiv.org/abs/2608.08636v2
• Date: Fri, 14 Aug 2026 04:03:09 GMT
• Title: Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach
• Abstract summary: Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts.<n>Recently, large language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort.<n>We propose TdSciNER, a type-driven approach that effectively leverages entity type information to enhance SciNER performance.
• Score: 12.37530494689998
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ROSE: Retrieval-Oriented Segmentation Enhancement [79.7370065070812]
  Existing segmentation models based on multimodal large language models (MLLMs) often struggle with novel or emerging entities due to their inability to incorporate up-to-date knowledge.<n>We introduce the Novel Emerging Task (NEST), which focuses on segmenting (i) novel entities that MLLMs fail to recognize due to their absence from training data, and (ii) emerging entities that exist within the model's knowledge but demand up-to-date information for accurate recognition.<n>Rose: Retrieval-Oriented Enhancement, a plug-and-play framework designed to augment any MLLM-based segmentation model,
  arXiv  Detail & Related papers  (2026-04-15T17:59:35Z)
• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition [53.019885776033824]
  We propose DynamicNER, the first NER dataset designed for Large Language Models (LLMs)-based methods with dynamic categorization.<n>The dataset is also multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains.<n>Experiments show that DynamicNER serves as a robust and effective benchmark for LLM-based NER methods.
  arXiv  Detail & Related papers  (2024-09-17T09:32:12Z)
• Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language Models [0.0]
  Few-Shot Prompting or in-context learning enables models to recognize entities with minimal examples. We assess state-of-the-art models like GPT-4 in NER tasks, comparing their few-shot performance to fully supervised benchmarks.
  arXiv  Detail & Related papers  (2024-08-28T13:42:28Z)
• ToNER: Type-oriented Named Entity Recognition with Generative Language Model [14.11486479935094]
  We propose a novel NER framework, namely ToNER based on a generative model. In ToNER, a type matching model is proposed at first to identify the entity types most likely to appear in the sentence. We append a multiple binary classification task to fine-tune the generative model's encoder, so as to generate the refined representation of the input sentence.
  arXiv  Detail & Related papers  (2024-04-14T05:13:37Z)
• ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models [25.68491572293656]
  Large Language Models fall short in structured knowledge extraction tasks such as named entity recognition. This paper explores an innovative, cost-efficient strategy to harness LLMs with modest NER capabilities for producing superior NER datasets.
  arXiv  Detail & Related papers  (2024-03-17T06:12:43Z)
• NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval [49.827932299460514]
  We argue that capabilities provided by large language models are not the end of NER research, but rather an exciting beginning. We present three variants of the NER task, together with a dataset to support them. We provide a large, silver-annotated corpus of 4 million paragraphs covering 500 entity types.
  arXiv  Detail & Related papers  (2023-10-22T12:23:00Z)
• Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach [50.12455129619845]
  Named Entity Recognition (NER) aims to extract and classify entity mentions in the text into pre-defined types. We propose to incorporate the label dependencies among entity types into a multi-task learning framework for better MRC-based NER.
  arXiv  Detail & Related papers  (2023-09-20T03:15:05Z)
• Dynamic Named Entity Recognition [5.9401550252715865]
  We introduce a new task: Dynamic Named Entity Recognition (DNER) DNER provides a framework to better evaluate the ability of algorithms to extract entities by exploiting the context. We evaluate baseline models and present experiments reflecting issues and research axes related to this novel task.
  arXiv  Detail & Related papers  (2023-02-16T15:50:02Z)
• MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective [57.19660234992812]
  NER model has achieved promising performance on standard NER benchmarks. Recent studies show that previous approaches may over-rely on entity mention information, resulting in poor performance on out-of-vocabulary (OOV) entity recognition. We propose MINER, a novel NER learning framework, to remedy this issue from an information-theoretic perspective.
  arXiv  Detail & Related papers  (2022-04-09T05:18:20Z)
• KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers [0.0]
  We propose a Knowledge Aware Representation Learning (KARL) Network for Named Entity Recognition (NER) KARL is based on a Transformer that utilizes large knowledge bases represented as fact triplets, converts them to a context, and extracts essential information residing inside to generate contextualized triplet representation for feature augmentation. Experimental results show that the augmentation done using KARL can considerably boost the performance of our NER system and achieve significantly better results than existing approaches in the literature on three publicly available NER datasets, namely CoNLL 2003, CoNLL++, and OntoNotes v5.
  arXiv  Detail & Related papers  (2021-11-30T14:29:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.