2 papers
cs.CL2026
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
Matteo Boglioni, Thibault Rousset, Siva Reddy +2
LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged a…
cs.CL2025
Merging Language and Domain Specific Models: The Impact on Technical Vocabulary Acquisition
Thibault Rousset, Taisei Kakibuchi, Yusuke Sasaki +1
Advancements in Natural Language Processing have enabled specialized language models, but integrating domain-specific knowledge into general-purpose models in multilingual settings…