Large Language Models (LLMs) have demonstrated remarkable In-Context learning (ICL) capabilities for relation extraction (RE). While ICL has shown promise in RE tasks, current approaches face challenges in example selection and utilization. These challenges stem from the misalignment between example selection methods and LLMs' inherent cognitive processing mechanisms, particularly in pattern recognition and relational reasoning. To address these limitations, we propose Counterfactual Cognitive Alignment (CCA), a novel framework that systematically enhances ICL performance in RE by aligning example selection with cognitive principles underlying human relational reasoning. The framework incorporates a cognitive-inspired counterfactual generation mechanism that creates semantically diverse yet relationally coherent examples, mirroring human "what-if" reasoning processes. Additionally, it employs a cognitive alignment approach that integrates structural identification features with semantic understanding to better align with LLMs cognitive processing patterns. Extensive experiments across multiple RE benchmarks reveal the effectiveness of our cognitive alignment approach through the synergistic integration of counterfactual reasoning and cognitively-guided selection.

Instruction tuning has emerged as an effective approach that notably improves large language models (LLMs) performance, showing particular promise in natural language generation tasks by producing more diverse, coherent, and task-relevant outputs. However, extending instruction tuning to natural language understanding (NLU) tasks presents significant challenges, primarily due to the difficulty in achieving high-precision responses and the scarcity of large-scale, high-quality instruction data necessary for effective tuning. In this work, we introduce Adversarial Noisy Instruction Tuning (ANIT) to improve NLU performance on LLMs. First, we leverage low-resource techniques to construct noisy instruction datasets. Second, we employ semantic distortion-aware techniques to quantify the intensity of noise within these instructions. Last, we devise an adversarial training method that incorporates a noise response strategy to achieve noisy instruction tuning. ANIT enhances LLMs capability to detect and accommodate semantic distortions in noisy instructions, thereby augmenting their comprehension of task objectives and ability to generate more accurate responses. We evaluate our approach across diverse noisy instructions and semantic distortion quantification methods on multiple NLU tasks. Comprehensive empirical results demonstrate that our method consistently outperforms existing approaches across various experimental settings.

Although vision foundation models such as SAM excel at natural image segmentation, their transfer to cross-modal medical segmentation remains difficult due to frequency mismatches, extreme scale variability, and modality-specific se-mantics. Existing adaptations typically require heavy fine-tuning and bespoke modules, which undermine generalization across diverse anatomies and imaging protocols. To address these chal-lenges, we propose CrossMed-SAM, which integrates three syner-gistic modules. The Cross-Frequency Attention Module (CFAM) leverages discrete wavelet transform to handle frequency domain variations across imaging modalities, while the Multi-Scale At-tention Module (MSAM) employs parallel dilated convolutions to capture extreme scale variations from microscopic lesions to large anatomical structures. The Adaptive Semantic Fusion Mod-ule (ASFM) integrates CLIP-based medical knowledge through dynamic gating mechanisms to provide semantic guidance when visual features are ambiguous. Extensive experiments on twelve datasets across five diverse medical imaging modalities demon-strate that CrossMed-SAM significantly outperforms existing state-of-the-art methods, achieving Dice coefficient improvements of 1.7% to 5.3% over the strong baseline MedSAM, with superior generalization capabilities across unseen datasets.

Large language models (LLMs) have significantly impacted the field of natural language processing (NLP). However, due to the limited domain specificity of the training data and the model’s constrained ability to generalize across complex biomedical data, LLMs continue to encounter challenges related to prediction bias and low generalization in biomedical named entity recognition (BioNER). In this work, we set out to improve the recognition and generalization capabilities of LLMs in BioNER through an Adversarial Selective Training (AST) method. Our method maximizes the adversarial loss to obtain the importance ranking of weights, which guides the model to selectively train to generate counterfactual examples. This strategy aims to force the model to explore the amount of information in the latent space to extract entities, thereby improving the performance of BioNER. Specifically, we conduct in-distribution experiments on five biomedical datasets and out-of-distribution experiments on two datasets. Experimental results show that our method outperforms other LLMs-based methods and significantly improves the performance of BioNER.

Joint entity and relation extraction (RE) construct a framework for unifying entity recognition and relationship extraction, and the approach can exploit the dependencies between the two tasks to improve the performance of the task. However, the existing tasks still have the following two problems. First, when the model extracts entity information, the boundary is blurred. Secondly, there are mostly implicit interactions between modules, that is, the interactive information is hidden inside the model, and the implicit interactions are often insufficient in the degree of interaction and lack of interpretability. To this end, this study proposes a joint entity and relation extraction model (ESEI) based on E fficient S ampling and E xplicit I nteraction. We innovatively divide negative samples into sentences based on whether they overlap with positive samples, which improves the model’s ability to extract entity word boundary information by controlling the sampling ratio. In order to increase the explicit interaction ability between the models, we introduce a heterogeneous graph neural network (GNN) into the model, which will serve as a bridge linking the entity recognition module and the relation extraction module, and enhance the interaction between the modules through information transfer. Our method substantially improves the model’s discriminative power on entity extraction tasks and enhances the interaction between relation extraction tasks and entity extraction tasks. Experiments show that the method is effective, we validate our method on four datasets, and for joint entity and relation extraction, our model improves the F1 score on multiple datasets.