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

arXiv: https://arxiv.org/abs/2605.03706 · HTML: https://mlsanity.com/paper/2605.03706/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 10 of 10)

- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction](https://mlsanity.com/paper/2403.07969/) (2024)
- [Schema-Driven Information Extraction from Heterogeneous Tables](https://mlsanity.com/paper/2305.14336/) (2023)
- [A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition](https://mlsanity.com/paper/2502.18702/) (2025)
- [Show Less, Instruct More: Enriching Prompts with Definitions and Guidelines for Zero-Shot NER](https://mlsanity.com/paper/2407.01272/) (2024)
- [GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction](https://mlsanity.com/paper/2506.00649/) (2025)

## Abstract (arXiv)

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 SAM-NER, a three-stage framework based on Semantic Archetype Mediation that stabilizes cross-domain transfer through an intermediate, domain-invariant archetype space. SAM-NER: (i) performs Entity Discovery via cooperative extraction and consensus-based denoising to obtain high-coverage, high-fidelity entity spans; (ii) conducts Abstract Mediation by projecting entities into a compact set of universal semantic archetypes distilled from high-level ontological abstractions; and (iii) applies 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.