← Search

Tuc Nguyen

2 accepted papers

2025

Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification

EMNLP 2025

Recent advancements in large language models (LLMs) have been fueled by large-scale training corpora drawn from diverse sources such as websites, news articles, and books. These datasets often contain explicit user information, such as person names, addresses, that LLMs may unintentionally reproduce

2024

Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning

ACL 2024long

Several parameter-efficient fine-tuning methods based on adapters have been proposed as a streamlined approach to incorporate not only a single specialized knowledge into existing Pre-Trained Language Models (PLMs) but also multiple of them at once. Recent works such as AdapterSoup propose to mix no…

Cited by 3SourcePDFScholar