# LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection

arXiv: https://arxiv.org/abs/2509.24547 · HTML: https://mlsanity.com/paper/2509.24547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality](https://mlsanity.com/paper/2310.07234/) (2023)
- [MAVEN: A Massive General Domain Event Detection Dataset](https://mlsanity.com/paper/2004.13590/) (2020)
- [Lifelong Language Pretraining with Distribution-Specialized Experts](https://mlsanity.com/paper/2305.12281/) (2023)
- [Mixture of Experts Meets Prompt-Based Continual Learning](https://mlsanity.com/paper/2405.14124/) (2024)
- [Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection](https://mlsanity.com/paper/2204.07275/) (2022)
- [Efficient Zero-shot Event Extraction with Context-Definition Alignment](https://mlsanity.com/paper/2211.05156/) (2022)
- [Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective](https://mlsanity.com/paper/2412.08285/) (2024)
- [Continual Few-shot Event Detection via Hierarchical Augmentation Networks](https://mlsanity.com/paper/2403.17733/) (2024)
- [Lifelong Event Detection via Optimal Transport](https://mlsanity.com/paper/2410.08905/) (2024)
- [Adaptive Few-Shot Learning (AFSL): Tackling Data Scarcity with Stability, Robustness, and Versatility](https://mlsanity.com/paper/2501.13479/) (2025)

## Abstract (arXiv)

Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approaches often suffer from severe forgetting due to the full fine-tuning of a shared base model, which leads to knowledge interference between tasks. Moreover, they frequently rely on data augmentation strategies that can introduce unnatural or semantically distorted inputs. To address these limitations, we propose LEAF, a novel and robust expert-based framework for FCED. LEAF integrates a specialized mixture of experts architecture into the base model, where each expert is parameterized with low-rank adaptation (LoRA) matrices. A semantic-aware expert selection mechanism dynamically routes instances to the most relevant experts, enabling expert specialization and reducing knowledge interference. To improve generalization in limited-data settings, LEAF incorporates a contrastive learning objective guided by label descriptions, which capture high-level semantic information about event types. Furthermore, to prevent overfitting on the memory buffer, our framework employs a knowledge distillation strategy that transfers knowledge from previous models to the current one. Extensive experiments on multiple FCED benchmarks demonstrate that LEAF consistently achieves state-of-the-art performance.