Challenge: Existing methods to improve lifelong event detection performance are limited by the limited stored examples.
Approach: They propose to use Episodic Memory Prompts to explicitly retain the learned task-specific knowledge.
Outcome: The proposed method can be used to update a model with new event types while retaining the capability on previously learned types.

Similar Papers

Domain Incremental Lifelong Learning in an Open World (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to lifelong learning (LL) models require access to task identities in the testing phase or cannot handle samples from unseen tasks.
Approach: They propose a dynamic architecture-based lifelong learning model that tries to learn a sequence of tasks with a prompt-enhanced language model.
Outcome: The proposed model outperforms state-of-the-art models in handling unseen tasks and focuses on task-level prompts to capture knowledge from different granularities.
Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits.
Approach: They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing.
Outcome: The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs.
Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent Detection (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods to identify all possible user intents at design time are expensive and require storage of past data.
Approach: They propose to continually train an intent detector on new intents while maintaining performance on prior intents.
Outcome: The proposed method outperforms exemplar replay-based approaches on lifelong intent detection tasks and achieves state-of-the-art on four public datasets.
Lifelong Event Detection with Embedding Space Separation and Compaction (2024.naacl-short)

Copied to clipboard

Challenge: Existing methods for event detection are prone to forgetting due to overlap between memory data and the previously learned embedding space.
Approach: They propose a method that embeds feature distributions away from the previous embedding space and mitigates overfitting by a memory calibration mechanism.
Outcome: The proposed method outperforms existing state-of-the-art methods with extensive experiments.
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue (2022.emnlp-main)

Copied to clipboard

Challenge: Existing generative replay methods use only a single task-specific token to control their models.
Approach: They propose a method to capture task-specific distributions with a conditional variational autoencoder, conditioned on natural language prompts to guide the pseudo-sample generation.
Outcome: The proposed method outperforms baselines on natural language understanding tasks of advanced task-oriented dialogue (ToD) systems.
Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods for continual prompt tuning are limited by the ever-growing parameter scale of modern language models (e.g., GPT-4 that may have 1.76 trillion parameters).
Approach: They propose a method for continual prompt tuning that enables the lifelong learning of a pre-trained language model by adding a task-specific prompt to a queue of older tasks.
Outcome: The proposed method outperforms the state-of-the-art methods substantially on continual prompt tuning benchmarks.
Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to correct outdated or erroneous knowledge in large language models (LLMs) are slow and cumbersome, resulting in catastrophic knowledge forgetting and degradation of model performance.
Approach: They propose a RetriEval-augmented ContInuous Prompt lEarning method that converts knowledge statements into short and informative continuous prompts, prefixed to the LLM’s input query embedding.
Outcome: The proposed method improves the performance of large language models (LLMs) while maintaining the overall performance of the model.
Lifelong Event Detection with Knowledge Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: Traditional supervised Information Extraction (IE) methods can extract structured knowledge elements from unstructured data, but it is limited to a pre-defined target ontology.
Approach: They propose a new lifelong event detection framework that is generalizable to other IE tasks and updates old knowledge with new event types’ mentions using a self-training loss.
Outcome: The proposed framework outperforms baselines with a 5.1% gain in the F1 score and can boost the F2 score for over 30% on some new long-tail rare event types with few training instances.
Prompts Can Play Lottery Tickets Well: Achieving Lifelong Information Extraction via Lottery Prompt Tuning (2023.acl-long)

Copied to clipboard

Challenge: Existing research on information extraction tasks focuses on one specific task, but in real-world scenarios, new data of different IE tasks and domains come in a stream over time.
Approach: They propose a parameter- and deployment-efficient prompt tuning method to evaluate the UIE system under a “lifelong learning” setting.
Outcome: The proposed method is able to learn new tasks without forgetting old ones and expand knowledge and functionalities without retraining the whole system.
EvoPrompt: Evolving Prompts for Enhanced Zero-Shot Named Entity Recognition with Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a low-resource task that requires supervised learning, but practical scenarios lack annotated data.
Approach: They propose an Evolving Prompts framework that guides the model to better address these issues through continuous prompt refinement.
Outcome: The proposed framework shows consistent performance improvements on four benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations