Longformer uses local windowed attention plus task-specific global attention to achieve linear scaling and state-of-the-art results on long-document language modeling, QA, and summarization after pretraining.
C o NLL -2012 Shared Task: Modeling Multilingual Unrestricted Coreference in O nto N otes
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.
citing papers explorer
-
Longformer: The Long-Document Transformer
Longformer uses local windowed attention plus task-specific global attention to achieve linear scaling and state-of-the-art results on long-document language modeling, QA, and summarization after pretraining.
-
Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution
Two-stage multilingual then dataset-specific adapter fine-tuning of Gemma-3-27b with headword XML mention representation and iterative annotation achieved first place in the CRAC 2026 LLM track.