Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
List Counting Failures Are Not One Phenomenon
Iyad Ait Hou, Saad Mankarious, Aya Zirikly +1
Counting the items in a bracketed list looks trivial, yet open-weight chat models often get it wrong. Prior work usually blames input bottlenecks such as subword fragmentation or a…
cs.LG2026
Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning
Iyad Ait Hou, Shrenik Borad, Harsh Sharma +3
Machine unlearning is increasingly important for clinical language models, where privacy regulations and institutional policies may require removing sensitive information from depl…