PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition Jinghui Lu1, Ziwei Y ang 1, Y anjie Wang
–Neural Information Processing Systems
The main cause of high latency in LLMs is the sequential decoding process, which autoregressively generates all labels and mentions for NER, significantly increase the sequence length.
Neural Information Processing Systems
Feb-18-2026, 07:21:28 GMT
- Country:
- Asia
- Europe
- Bulgaria > Sofia City Province
- Sofia (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Italy (0.04)
- United Kingdom > England (0.04)
- Bulgaria > Sofia City Province
- North America
- Canada > Ontario
- Toronto (0.04)
- United States (0.04)
- Canada > Ontario
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Victoria > Melbourne (0.04)
- South America > Colombia
- Meta Department > Villavicencio (0.04)
- Genre:
- Overview (0.68)
- Research Report > Experimental Study (0.93)
- Industry:
- Health & Medicine (0.46)
- Information Technology (0.46)
- Technology: