← Search

Feng Yichao

2 accepted papers

2025

Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation

NAACL 2025long

Previous research on multimodal entity linking (MEL) has primarily employed contrastive learning as the primary objective. However, using the rest of the batch as negative samples without careful consideration, these studies risk leveraging easy features and potentially overlook essential details th…

Cited by 2SourcePDFScholar
2025

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

ACL 2025finding

Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models (LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious attacks. Research indicates that poisoned LLMs, even after PEFT, retain the capability to activate internalized backdoors when in…