4 papers
On Extending Direct Preference Optimization to Accommodate Ties
Jinghong Chen, Guangyu Yang, Weizhe Lin +2
We derive and investigate two DPO variants that explicitly model the possibility of declaring a tie in pair-wise comparisons. We replace the Bradley-Terry model in DPO with two wel…
Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
Guangyu Yang, Jinghong Chen, Jingbiao Mei +2
Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose ma…
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection
Jingbiao Mei, Jinghong Chen, Guangyu Yang +2
Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hatefu…
Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning
Jingbiao Mei, Jinghong Chen, Weizhe Lin +2
Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our invest…