In-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios. However, existing ICL-based NER methods suffer from three key limitations: (1) reliance on dynamic retrieval of annotated examples, which is problematic when annotated data is scarce; (2) limited generalization to unseen domains due to the LLM's insufficient internal domain knowledge; and (3) failure to incorporate external knowledge or resolve entity ambiguities. To address these challenges, we propose KDR-Agent, a novel multi-agent framework for multi-domain low-resource in-context NER that integrates Knowledge retrieval, Disambiguation, and Reflective analysis. KDR-Agent leverages natural-language type definitions and a static set of entity-level contrastive demonstrations to reduce dependency on large annotated corpora. A central planner coordinates specialized agents to (i) retrieve factual knowledge from Wikipedia for domain-specific mentions, (ii) resolve ambiguous entities via contextualized reasoning, and (iii) reflect on and correct model predictions through structured self-assessment. Experiments across ten datasets from five domains demonstrate that KDR-Agent significantly outperforms existing zero-shot and few-shot ICL baselines across multiple LLM backbones.

Stance detection aims to identify the attitude expressed in text towards a specific target.Recent studies on zero-shot and few-shot stance detection focus primarily on learning generalized representations from explicit targets.However, these methods often neglect implicit yet semantically important targets and fail to adaptively adjust the relative contributions of text and target in light of contextual dependencies.To overcome these limitations, we propose a novel two-stage framework: First, a data augmentation framework named Hierarchical Collaborative Target Augmentation (HCTA) employs Large Language Models (LLMs) to identify and annotate implicit targets via Chain-of-Thought (CoT) prompting and multi-LLM voting, significantly enriching training data with latent semantic relations.Second, we introduce DyMCA, a Dynamic Multi-level Contextaware Attention Network, integrating a joint text-target encoding and a content-aware mechanism to dynamically adjust text-target contributions based on context.Experiments on the benchmark dataset demonstrate that our approach achieves state-of-the-art results, confirming the effectiveness of implicit target augmentation and fine-grained contextual modeling.Our code is publicly available at https: //github.com/EliaukoaYoW/DyMCA.

Large-scale biomedical entity recognition and relation extraction are essential foundational tasks for downstream text mining tasks and applications, such as knowledge graph construction. Because many relations span sentence boundaries, document-level entity recognition and relation extraction is closely aligned with real-world demands. However, identifying complex and diverse entities and relations within a limited timeframe is challenging. Therefore, we propose an end-to-end approach called BioECR for biomedical document-level named entity recognition, coreference resolution, and relation extraction. This approach utilizes a bi-encoder structure combined with biomedical entity types and descriptions to solve nested biomedical entities in linear time, thereby enhancing the ability to recognise complex entities and relations. Then a composition graph convolutional neural network was proposed to address the noise in conventional graph convolutional networks, thereby reducing time overhead and selectively fusing multiple entities or contextual information. Finally, by combining entity type clustering methods, the problem of coreference errors among multiple types of entities is solved easily and quickly. Experimental results demonstrate that our approach achieves state-of-the-art performance on all subtasks across three biomedical document-level datasets called CDR, GDA, and BioRED, and our approach reduces the inference time by approximately 60%.

In the biomedical field, information is widely distributed across numerous pieces of literature. Extracting events between entities from biomedical texts has garnered significant attention in recent years. However, previous research primarily focus on extracting flat biomedical events, with less attention given to nested biomedical events. Moreover, existing methods for extracting nested events often overlook the long-distance dependencies and global information between trigger words and arguments within events, and they lack sufficient interaction with event type information. To address these issues, we propose a semantic segmentation-based method for extracting nested biomedical events. We introduce U-Net to capture global information and interdependencies between event entities. Additionally, we map event types to natural language text and combine them with sentences for encoding to enhance interaction. We also employ two auxiliary tasks to improve the identification of trigger words and arguments. Finally, events are extracted by identifying the four vertices of the segmented region. Experimental results on two benchmark datasets show that our method excels in recognizing nested biomedical events and outperforms current state-of-the-art methods.

OBJECTIVE: Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on diverse biomedical natural language processing (NLP) tasks in different languages, we present Taiyi, a bilingual fine-tuned LLM for diverse biomedical NLP tasks. MATERIALS AND METHODS: We first curated a comprehensive collection of 140 existing biomedical text mining datasets (102 English and 38 Chinese datasets) across over 10 task types. Subsequently, these corpora were converted to the instruction data used to fine-tune the general LLM. During the supervised fine-tuning phase, a 2-stage strategy is proposed to optimize the model performance across various tasks. RESULTS: Experimental results on 13 test sets, which include named entity recognition, relation extraction, text classification, and question answering tasks, demonstrate that Taiyi achieves superior performance compared to general LLMs. The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multitasking. CONCLUSION: Leveraging rich high-quality biomedical corpora and developing effective fine-tuning strategies can significantly improve the performance of LLMs within the biomedical domain. Taiyi shows the bilingual multitasking capability through supervised fine-tuning. However, those tasks such as information extraction that are not generation tasks in nature remain challenging for LLM-based generative approaches, and they still underperform the conventional discriminative approaches using smaller language models.

Document-level interaction extraction for Chemical-Disease is aimed at inferring the interaction relations between chemical entities and disease entities across multiple sentences. Compared with sentence-level relation extraction, document-level relation extraction can capture the associations between different entities throughout the entire document, which is found to be more practical for biomedical text information. However, current biomedical extraction methods mainly concentrate on sentence-level relation extraction, making it difficult to access the rich structural information contained in documents in practical application scenarios. We put forward SSGU-CD, a combined Semantic and Structural information Graph U-shaped network for document-level Chemical-Disease interaction extraction. This framework effectively stores document semantic and structure information as graphs and can fuse the original context information of documents. Using the framework, we propose a balanced combination of cross-entropy loss function to facilitate collaborative optimization among models with the aim of enhancing the ability to extract Chemical-Disease interaction relations. We evaluated SSGU-CD on the document-level relation extraction dataset CDR and BioRED, and the results demonstrate that the framework can significantly improve the extraction performance.

The Relational Triple Extraction (RTE) task is a fundamental and essential information extraction task.Recently, the table-filling RTE methods have received lots of attention.Despite their success, they suffer from some inherent problems such as underutilizing regional information of triple.In this work, we treat the RTE task based on table-filling method as an Object Detection task and propose a one-stage Object Detection framework for Relational Triple Extraction (OD-RTE).In this framework, the vertices-based bounding box detection, coupled with auxiliary global relational triple region detection, ensuring that regional information of triple could be fully utilized.Besides, our proposed decoding scheme could extract all types of triples.In addition, the negative sampling strategy of relations in the training stage improves the training efficiency while alleviating the imbalance of positive and negative relations.The experimental results show that 1) OD-RTE achieves the state-of-the-art performance on two widely used datasets (i.e., NYT and WebNLG).2) Compared with the best performing table-filling method, OD-RTE achieves faster training and inference speed with lower GPU memory usage.To facilitate future research in this area, the codes are publicly available at https://github.com/NingJinzhong/ODRTE.

Automatic extraction of biomedical entities and their relations plays a significant role in biomedical curation tasks. Currently, the table-filling methods have received lots of attention in the general domain. However, the presence of complex lengthy sentences and overlapping relations in biomedical texts makes automatic extraction a challenging task. To address this challenge, we propose a joint extraction table-filling method based on the vertices of the triple region. We extract triples by using multi-label classification to mark the boundaries of the triples, fully utilizing the boundary information of the entities. To incorporate the information of the distance between entity pairs, distance embedding is introduced and dilated convolutions are utilized to capture multi-scale contextual information. We evaluated our model on the CHEMPROT and DDIExtraction2013 datasets. The experimental results demonstrate that our model achieves the state-of-the-art performance on both datasets.

The task of extracting overlapping and nested events has received significant attention in recent times, as prior research has primarily focused on extracting flat events, overlooking the intricacies of overlapping and nested occurrences. In this work, we present a new approach to Event Extraction (EE) by reformulating it as an object detection task on a table of token pairs. Our proposed one-stage event extractor, called ODEE, can handle overlapping and nested events. The model is designed with a vertex-based tagging scheme and two auxiliary tasks of predicting the spans and types of event trigger words and argument entities, leveraging the full span information of event elements. Furthermore, in the training stage, we introduce a negative sampling method for table cells to address the imbalance problem of positive and negative table cell tags, meanwhile improving computational efficiency. Empirical evaluations demonstrate that ODEE achieves the state-of-the-art performance on three benchmarks for overlapping and nested EE (i.e., FewFC, Genia11, and Genia13). Furthermore, ODEE outperforms current state-of-the-art methods in terms of both number of parameters and inference speed, indicating its high computational efficiency. To facilitate future research in this area, the codes are publicly available at https://github.com/NingJinzhong/ODEE.

Biomedical named entity recognition (Bio-NER) is an essential task for biomedical information extraction. In this paper, we regard word-level features and character-level features as two different modalities from a novel perspective and propose a biomedical named entity recognition model based on character feature enhancement with multimodal method (called BioNER-CFEM). BioNER-CFEM can not only capture interactions between modalities, but also learn interactions within modalities. In addition, our proposed cross-attention based sparse selection mechanism can effectively alleviate the noise in the interaction process of the two ‘modalities’. Experimental results show the effectiveness of BioNER-CFEM for the Bio-NER task: it achieves performance boost over SOTA models with competitive efficiency on all six Bio-NER datasets, i.e., $+0.89, +0.64, +0.40$, $+1.40, +5.57, +2.81$ on NCBI-Disease, BC5CDR-Disease, BC5CDR-Chem, BC2GM, JNLPBA, BC4CHEMD, respectively.

Chinese Named Entity Recognition (NER) has continued to attract research attention. However, most existing studies only explore the internal features of the Chinese language but neglect other lingual modal features. Actually, as another modal knowledge of the Chinese language, English contains rich prompts about entities that can potentially be applied to improve the performance of Chinese NER. Therefore, in this study, we explore the bilingual enhancement for Chinese NER and propose a unified bilingual interaction module called the Adapted Cross-Transformers with Global Sparse Attention (ACT-S) to capture the interaction of bilingual information. We utilize a model built upon several different ACT-Ss to integrate the rich English information into the Chinese representation. Moreover, our model can learn the interaction of information between bilinguals (inter-features) and the dependency information within Chinese (intra-features). Compared with existing Chinese NER methods, our proposed model can better handle entities with complex structures. The English text that enhances the model is automatically generated by machine translation, avoiding high labour costs. Experimental results on four well-known benchmark datasets demonstrate the effectiveness and robustness of our proposed model.

The goal of relation extraction task is to classify texts containing entity pairs into predefined relation types. Biomedical relation extraction can extract high-quality information from massive medical texts, which plays an important role in biomedical research. In this paper, we propose a self-supervised graph attention network to extract biomedical relations from the complex and noisy biomedical texts. The model incorporates self-supervision within the standard graph attention mechanism. Specifically, the model applies the graph attention mechanism to reduce the influence of noisy words and introduces dependency-based parse trees to construct a self-supervised task. With the supervision of dependency-based parse trees, the graph attention network can not only improve its capacity of learning syntactic information but also alleviate its lack of interpretability. Additionally, we use Gumbel Tree-GRU to obtain sentence information for relation classification. Our model achieves state-of-the-art performance on the DDIExtraction 2013 and ChemProt datasets, respectively, which suggests that our proposed model can effectively improve the performance of biomedical relation extraction.