Papers by Sirry Chen
CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for social media bot detection neglect community structure and poor model generalization due to the relatively small scale of the dataset. |
| Approach: | They propose a framework that constructs social networks as heterogeneous graphs and uses community-aware modules to mine hard positive and hard negative samples for supervised graph contrastive learning. |
| Outcome: | The proposed framework outperforms baselines on three social media bot benchmarks. |
SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in speech language models have enabled more natural speech-based interactions, but the scarcity of medical speech data and the inefficiency of fine-tuning on speech data hinder adoption of SpeechLMs in medical consultation. |
| Approach: | They propose a SpeechLM natively capable of conducting speech-based multi-turn interactions with patients. |
| Outcome: | The proposed model outperforms baselines in both effectiveness and robustness in most evaluation settings. |