Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach
Tong Bao, Yi Zhao, Heng Zhang, Chengzhi Zhang
cs.CL, cs.AI, cs.DL, cs.IR
Submitted: 2026-08-14
Updated: 2026-08-17
Journal ref: Expert Systems With Applications, 2026
DOI: 10.1016/j.eswa.2026.133983
Code: https://github.com/tongbao96/codefor-SciNER
License: http://creativecommons.org/licenses/by/4.0/
The gist: Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts.
Terminology
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.
Sources
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing
- Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering
- LoRA: Low-Rank Adaptation of Large Language Models
- Bidirectional LSTM-CRF Models for Sequence Tagging
- Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition
- P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
- InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
- GPT-NER: Named Entity Recognition via Large Language Models
- InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
- Empirical Study of Zero-Shot NER with ChatGPT
- Show Less, Instruct More: Enriching Prompts with Definitions and Guidelines for Zero-Shot NER
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering