Papers by Keyu Yao
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)
Copied to clipboard
Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang
| Challenge: | Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts. |
| Approach: | They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships. |
| Outcome: | The proposed model improves in role-play settings and in e-commerce and recommendation systems. |
SGCD: Subtask-Guided Causal-Debiasing Framework for Robust Cross-Utterance Sentiment Quadruple Extraction in Dialogues (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new framework for sentiment analysis in dialogues addresses cross-utterance elements and focus biases . SGCD framework employs multi-granularity attention paths to enhance cross-interaction matching . |
| Approach: | a framework is developed to help analyze sentiments in multi-turn dialogues . it leverages subtask-specific features to guide learning of token-level features . |
| Outcome: | The proposed framework outperforms state-of-the-art methods in analyzing conversational data . cross-utterance elements and focus bias are challenges, authors say . |