# Limited Effectiveness of LLM-based Data Augmentation for COVID-19 Misinformation Stance Detection

arXiv: https://arxiv.org/abs/2503.02328 · HTML: https://mlsanity.com/paper/2503.02328/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [Combining Fact Extraction and Verification with Neural Semantic Matching Networks](https://mlsanity.com/paper/1811.07039/) (2018)
- [Combating Misinformation in the Age of LLMs: Opportunities and Challenges](https://mlsanity.com/paper/2311.05656/) (2023)
- [A Survey on Stance Detection for Mis- and Disinformation Identification](https://mlsanity.com/paper/2103.00242/) (2021)
- [AEDA: An Easier Data Augmentation Technique for Text Classification](https://mlsanity.com/paper/2108.13230/) (2021)
- [FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs](https://mlsanity.com/paper/2402.05904/) (2024)
- [Characterizing and Predicting Social Correction on Twitter](https://mlsanity.com/paper/2303.08889/) (2023)
- [Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection](https://mlsanity.com/paper/1911.11951/) (2019)
- [The COVMis-Stance dataset: Stance Detection on Twitter for COVID-19 Misinformation](https://mlsanity.com/paper/2204.02000/) (2022)
- [Cross-Target Stance Detection: A Survey of Techniques, Datasets, and Challenges](https://mlsanity.com/paper/2409.13594/) (2024)

## Built on by (most cited first, 7 of 7)

- [Debunk and Infer: Multimodal Fake News Detection via Diffusion-Generated Evidence and LLM Reasoning](https://mlsanity.com/paper/2506.21557/) (2025)
- [Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security](https://mlsanity.com/paper/2605.23989/) (2026)
- [MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform](https://mlsanity.com/paper/2506.00308/) (2025)
- [DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales](https://mlsanity.com/paper/2508.10444/) (2025)
- [Wisdom of the LLM Crowd: A Large Scale Benchmark of Multi-Label U.S. Election-Related Harmful Social Media Content](https://mlsanity.com/paper/2602.11962/) (2026)
- [Angry but Accurate: Detecting and Profiling the Counter-Misinformation Ecosystem on Twitter](https://mlsanity.com/paper/2607.02900/) (2026)
- [SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection](https://mlsanity.com/paper/2610.13207/) (2026)

## Abstract (arXiv)

Misinformation surrounding emerging outbreaks poses a serious societal threat, making robust countermeasures essential. One promising approach is stance detection (SD), which identifies whether social media posts support or oppose misleading claims. In this work, we finetune classifiers on COVID-19 misinformation SD datasets consisting of claims and corresponding tweets. Specifically, we test controllable misinformation generation (CMG) using large language models (LLMs) as a method for data augmentation. While CMG demonstrates the potential for expanding training datasets, our experiments reveal that performance gains over traditional augmentation methods are often minimal and inconsistent, primarily due to built-in safeguards within LLMs. We release our code and datasets to facilitate further research on misinformation detection and generation.