# Continuous Detection, Rapidly React: Unseen Rumors Detection based on Continual Prompt-Tuning

arXiv: https://arxiv.org/abs/2203.11720 · HTML: https://mlsanity.com/paper/2203.11720/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks](https://mlsanity.com/paper/2001.06362/) (2020)
- [Detection and Resolution of Rumours in Social Media: A Survey](https://mlsanity.com/paper/1704.00656/) (2017)
- [Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning](https://mlsanity.com/paper/2112.02706/) (2021)
- [Fighting an Infodemic: COVID-19 Fake News Dataset](https://mlsanity.com/paper/2011.03327/) (2020)
- [A Survey on Natural Language Processing for Fake News Detection](https://mlsanity.com/paper/1811.00770/) (2018)
- [La-MAML: Look-ahead Meta Learning for Continual Learning](https://mlsanity.com/paper/2007.13904/) (2020)
- [Efficient Meta Lifelong-Learning with Limited Memory](https://mlsanity.com/paper/2010.02500/) (2020)
- [Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.03271/) (2021)
- [Meta-Consolidation for Continual Learning](https://mlsanity.com/paper/2010.00352/) (2020)
- [Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning](https://mlsanity.com/paper/2104.08808/) (2021)
- [A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation](https://mlsanity.com/paper/2203.01670/) (2022)
- [Fake News Early Detection: An Interdisciplinary Study](https://mlsanity.com/paper/1904.11679/) (2019)
- [Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks](https://mlsanity.com/paper/2110.04522/) (2021)
- [Multimodal Emergent Fake News Detection via Meta Neural Process Networks](https://mlsanity.com/paper/2106.13711/) (2021)
- [AutoRC: Improving BERT Based Relation Classification Models via Architecture Search](https://mlsanity.com/paper/2009.10680/) (2020)
- [Dynamically Addressing Unseen Rumor via Continual Learning](https://mlsanity.com/paper/2104.08775/) (2021)

## Built on by (most cited first, 12 of 12)

- [MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning](https://mlsanity.com/paper/2410.18035/) (2024)
- [F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks](https://mlsanity.com/paper/2305.11916/) (2023)
- [Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities](https://mlsanity.com/paper/2203.13883/) (2022)
- [AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System](https://mlsanity.com/paper/2510.01617/) (2025)
- [PARA: Parameter-Efficient Fine-tuning with Prompt Aware Representation Adjustment](https://mlsanity.com/paper/2502.01033/) (2025)
- [Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generator](https://mlsanity.com/paper/2504.04076/) (2025)
- [MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine](https://mlsanity.com/paper/2601.16503/) (2026)
- [Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors](https://mlsanity.com/paper/2507.05939/) (2025)
- [Evaluating ChatGPT on Medical Information Extraction Tasks: Performance, Explainability and Beyond](https://mlsanity.com/paper/2601.21767/) (2026)
- [ACL: Aligned Contrastive Learning Improves BERT and Multi-exit BERT Fine-tuning](https://mlsanity.com/paper/2602.03563/) (2026)
- [Variety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations](https://mlsanity.com/paper/2508.03420/) (2025)
- [A Generative Model for Joint Multiple Intent Detection and Slot Filling](https://mlsanity.com/paper/2602.08322/) (2026)

## Abstract (arXiv)

Since open social platforms allow for a large and continuous flow of unverified information, rumors can emerge unexpectedly and spread quickly. However, existing rumor detection (RD) models often assume the same training and testing distributions and can not cope with the continuously changing social network environment. This paper proposed a Continual Prompt-Tuning RD (CPT-RD) framework, which avoids catastrophic forgetting (CF) of upstream tasks during sequential task learning and enables bidirectional knowledge transfer between domain tasks. Specifically, we propose the following strategies: (a) Our design explicitly decouples shared and domain-specific knowledge, thus reducing the interference among different domains during optimization; (b) Several technologies aim to transfer knowledge of upstream tasks to deal with emergencies; (c) A task-conditioned prompt-wise hypernetwork (TPHNet) is used to consolidate past domains. In addition, CPT-RD avoids CF without the necessity of a rehearsal buffer.