aiqbench analysis
Just Pass Twice (JPT) offers a significant efficiency breakthrough for zero-shot Named Entity Recognition by enabling causal LLMs to utilize full bidirectional context without architectural changes. By simply concatenating the input sequence, this method achieves state-of-the-art F1 scores while being over 20x faster than traditional generative approaches that suffer from hallucinations and slow decoding. This advancement directly addresses a core limitation in current LLM applications for discriminative tasks, making high-accuracy entity extraction more practical for production environments.
Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER
arXiv:2604.05158v3 Announce Type: replace Abstract: Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, where tokens attend only to preceding context, prevents effective token classification when disambiguation requires future context. Existing approaches use LLMs generatively, prompting them to list entities or produce structured outputs, but suffer from slow autoregressive decoding, hallucinated entities, and formatting errors. We propose Just Pass Twice (JPT), a simple yet effective method that enables causal LLMs to perform discriminative token classification with full bidirectional context. Our key insight is that concatenating the input to itself lets each token in the second pass attend to the complete sentence, requiring no architectural modifications. We combine these representations with definition-guided entity embeddings for flexible zero-shot generalization. Our approach achieves state-of-the-art results on zero-shot NER benchmarks, surpassing the previous best method by +7.9 F1 on average across CrossNER and MIT benchmarks, being over 20x faster than comparable generative methods. Interactive demo and access to the model are available at https://witness-ai-jpt-ner.hf.space/
Abstract:Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, where tokens attend only to preceding context, prevents effective token classification when disambiguation requires future context. Existing approaches use LLMs generatively, prompting them to list entities or produce structured outputs, but suffer from slow autoregressive decoding, hallucinated entities, and formatting errors. We propose Just Pass Twice (JPT), a simple yet effective method that enables causal LLMs to perform discriminative token classification with full bidirectional context. Our key insight is that concatenating the input to itself lets each token in the second pass attend to the complete sentence, requiring no architectural modifications. We combine these representations with definition-guided entity embeddings for flexible zero-shot generalization. Our approach achieves state-of-the-art results on zero-shot NER benchmarks, surpassing the previous best method by +7.9 F1 on average across CrossNER and MIT benchmarks, being over 20x faster than comparable generative methods. Interactive demo and access to the model are available at this https URL
16 pages, 9 figures, 12 tables. Published in Proceedings of ACL 2026 (Volume 1: Long Papers), pages 11480-11497. Demo and API: this https URL
Computation and Language (cs.CL)
arXiv:2604.05158 [cs.CL]
(or arXiv:2604.05158v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2604.05158 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.18653/v1/2026.acl-long.526 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 293 words
Related coverage
Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT
METR · Jul 21, 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
Informe de riesgos de la IA de frontera (febrero–marzo de 2026)
METR · May 19, 2026
Frontier AI Risk Report (February–March 2026)
METR · May 19, 2026