SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition

• URL: http://arxiv.org/abs/2605.03706v1
• Date: Tue, 05 May 2026 12:54:17 GMT
• Title: SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition
• Abstract summary: emphSemantic Archetype Mediation stabilizes cross-domain transfer through an intermediate, domain-invariant archetype space.<n> SAM-NER consistently outperforms strong prior ZS-NER baselines in cross-domain settings.
• Score: 50.82878172248818
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large language model's (LLM's) intrinsic semantic organization. As a result, directly mapping entity mentions to fine-grained target labels can induce systematic semantic drift, especially when target schemas are novel or semantically overlapping. We propose \textbf{SAM-NER}, a three-stage framework based on \emph{Semantic Archetype Mediation} that stabilizes cross-domain transfer through an intermediate, domain-invariant archetype space. SAM-NER: (i) performs \emph{Entity Discovery} via cooperative extraction and consensus-based denoising to obtain high-coverage, high-fidelity entity spans; (ii) conducts \emph{Abstract Mediation} by projecting entities into a compact set of universal semantic archetypes distilled from high-level ontological abstractions; and (iii) applies \emph{Semantic Calibration} to resolve archetype-level predictions into target-domain types through constrained, definition-aligned inference with a frozen LLM. Experiments on the CrossNER benchmark show that SAM-NER consistently outperforms strong prior ZS-NER baselines in cross-domain settings. Our implementation will be open-sourced at https://github.com/DMIRLAB-Group/SAM-NER.

Related papers

• LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation [43.56251979741165]
  Domain Generalization Semantic (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains.<n>Style randomization distorts the underlying feature manifold due to its coarse-grained nature.<n>Feature normalization suppresses discnative, domain-sensitive semantic details owing to its rigid design.
  arXiv  Detail & Related papers  (2026-08-09T16:43:04Z)
• Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation [8.277992670183004]
  Cross-domain Few-shot (CD-FSS) aims to learn generalizable segmentation capability from abundant annotated samples in the source domain.<n>Our method achieves state-of-the-art performance on four target-domain datasets.
  arXiv  Detail & Related papers  (2026-06-23T08:18:53Z)
• Learning a Semantic Calibration Network for Open-Vocabulary Semantic Segmentation [5.122331812021513]
  Open-Vocabulary (OVS) extends the segmentation task from a fixed set to an open set.<n>We propose a novel Semantic Network (SCN) for open-vocabulary semantic segmentation.<n>The proposed method achieves significant performance improvements compared to state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2026-06-06T06:42:03Z)
• Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation [37.61604558855609]
  Universal Domain Adaptation (UniDA) focuses on transferring source domain knowledge to the target domain under both domain shift and unknown category shift.<n>Current methods typically obtain target domain semantics centers from an unconstrained continuous image representation space.<n>In this paper, based on vision-language models, we search for semantic centers in a semantically meaningful and discrete text representation space.
  arXiv  Detail & Related papers  (2025-06-04T03:11:53Z)
• StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
  Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data. We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
  arXiv  Detail & Related papers  (2024-06-01T02:41:34Z)
• Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation [108.40945109477886]
  We propose a novel SSDA approach named Graph-based Adaptive Betweenness Clustering (G-ABC) for achieving categorical domain alignment. Our method outperforms previous state-of-the-art SSDA approaches, demonstrating the superiority of the proposed G-ABC algorithm.
  arXiv  Detail & Related papers  (2024-01-21T09:57:56Z)
• Regularizing Self-training for Unsupervised Domain Adaptation via Structural Constraints [14.593782939242121]
  We propose to incorporate structural cues from auxiliary modalities, such as depth, to regularise conventional self-training objectives. Specifically, we introduce a contrastive pixel-level objectness constraint that pulls the pixel representations within a region of an object instance closer. We show that our regularizer significantly improves top performing self-training methods in various UDA benchmarks for semantic segmentation.
  arXiv  Detail & Related papers  (2023-04-29T00:12:26Z)
• Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning [80.36076044023581]
  We present an efficient bi-encoder framework for named entity recognition (NER) We frame NER as a metric learning problem that maximizes the similarity between the vector representations of an entity mention and its type. A major challenge to this bi-encoder formulation for NER lies in separating non-entity spans from entity mentions.
  arXiv  Detail & Related papers  (2022-08-30T23:19:04Z)
• Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation [85.6961770631173]
  In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. We propose a novel approach called Cross-domain Adaptive Clustering to address this problem.
  arXiv  Detail & Related papers  (2021-04-19T16:07:32Z)
• Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation [67.37606333193357]
  We propose aSimultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains. By leveraging target pseudo-labels, a robust triplet-centroid alignment mechanism is explicitly applied to align feature representations for each category. Experiments on various HDA tasks across text-to-image, image-to-image and text-to-text successfully validate the superiority of our SSAN against state-of-the-art HDA methods.
  arXiv  Detail & Related papers  (2020-08-04T16:20:37Z)

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.