Dongliang Guo

Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification

LLMs Are Too Smart to Be Average: Controlling LLM Proficiency via Guided Decoding

Revisiting Dynamic Graphs from the Perspective of Time Series

Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing