Our paper is accepted to IJCNLP-AACL 2025.
Our paper “Persona is a Double-Edged Sword: Rethinking the Impact of Role-playing Prompts in Zero-shot Reasoning Tasks” has been accepted to IJCNLP-AACL 2025...
Our paper “Persona is a Double-Edged Sword: Rethinking the Impact of Role-playing Prompts in Zero-shot Reasoning Tasks” has been accepted to IJCNLP-AACL 2025...
Our papers “FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge” and “Avoidance Decoding for Diverse ...
Our paper “Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time” has been accepted to CIKM 2025.
I joined Max Planck Institute for Security and Privacy as a research intern.
Our paper “MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors” has been accepted to CIKM 2024. This Wor...