Papers by Fengzhu Zeng
Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for few-shot and zero-shot fact verification require a large set of training data. |
| Approach: | They propose a method to prompt pre-trained language models to be consistent to improve the factuality assessment capability of PLMs. |
| Outcome: | The proposed method outperforms state-of-the-art few-shot fact verification models with a small number of unlabeled instances on zero-shot verification. |
Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Obtaining large-scale, high-quality real-world fact-checking datasets is costly . generalizability of detectors trained on synthetic data to real-life scenarios remains unclear . |
| Approach: | They propose to use synthetic data to learn from real-world data to detect multimodal misinformation . they propose to combine model-agnostic data selection methods with real-life data distributions . |
| Outcome: | The proposed method improves the performance of a small MLLM on real-world fact-checking datasets, surpassing GPT-4V. |
Early Rumor Detection Using Neural Hawkes Process with a New Benchmark Dataset (2022.naacl-main)
Copied to clipboard
| Challenge: | rumor detection models have been designed with oversimplifcation and evaluated inappropriately on a few datasets where the actual early-stage information is largely missing. |
| Approach: | They propose a new Benchmark dataset for EArly Rumor Detection based on claims from fact-checking websites and a novel model based upon neural Hawkes process for EARD. |
| Outcome: | The proposed model can guide a generic rumor detection model to make timely, accurate and stable predictions. |