Papers by Wei-Yao Wang
Benchmarking Agentic Newswriting via Journalistic Workflows (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in autonomous digital agents highlight their potential for structured tasks through autonomous decision-making and task decomposition, but it remains unclear how well such systems support real-world information-intensive workflows. |
| Approach: | They propose a benchmark to evaluate how journalists can use agents to organize and organize information from the web. |
| Outcome: | The proposed system can be used to iterate and evaluate newswriting tasks in real-world situations. |
Style-News: Incorporating Stylized News Generation and Adversarial Verification for Neural Fake News Detection (2024.eacl-long)
Copied to clipboard
| Challenge: | Using generative models, the issues of producing hallucinatory contents have been raised in various domains, e.g., law, writing. |
| Approach: | They propose a style-aware neural news generator that mimics the style of real news to deceive people by identifying which publisher the style corresponds to and training a model to detect fake news. |
| Outcome: | The proposed framework outperforms state-of-the-art models in terms of fluency, content preservation, and style adherence. |
RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing intent detection approaches have relied on adaptively pre-training language models with large-scale datasets, yet the predominant cost of data collection may hinder their superiority. |
| Approach: | They propose a self-supervised framework dedicated to task-oriented dialogues which incorporates agent responses for pre-training in a two-stage manner. |
| Outcome: | The proposed framework outperforms the state-of-the-art frameworks for task-oriented dialogues on two real-world customer service datasets. |