# Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER

arXiv: https://arxiv.org/abs/2604.05158 · HTML: https://mlsanity.com/paper/2604.05158/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Efficient Training of Language Models to Fill in the Middle](https://mlsanity.com/paper/2207.14255/) (2022)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [Named Entity Recognition with Bidirectional LSTM-CNNs](https://mlsanity.com/paper/1511.08308/) (2015)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding](https://mlsanity.com/paper/1909.02188/) (2019)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data](https://mlsanity.com/paper/2402.15343/) (2024)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study](https://mlsanity.com/paper/2401.10825/) (2024)
- [Improving Minimum Bayes Risk Decoding with Multi-Prompt](https://mlsanity.com/paper/2407.15343/) (2024)
- [A Systematic Characterization of LLM Inference on GPUs](https://mlsanity.com/paper/2512.01644/) (2025)
- [Multi-Prompting Decoder Helps Better Language Understanding](https://mlsanity.com/paper/2406.06279/) (2024)

## Abstract (arXiv)

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/