Zafar Takhirov — accepted AI-conference papers

2026

Label Smoothing Improves Machine Unlearning

Zonglin Di, Zhaowei Zhu, Jinghan Jia, Jiancheng Liu, Zafar Takhirov, Bo Jiang +3

ICLR 2026poster

The objective of machine unlearning (MU) is to eliminate previously learned data from a model. However, it can be challenging to strike a balance between computation cost and performance when using existing MU techniques. Taking inspiration from the influence of label smoothing on model confidence a…

Cited by 0 Source ↗Scholar ↗

2025

Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models

James Flemings, Bo Jiang, Wanrong Zhang, Zafar Takhirov, Murali Annavaram

ACL 2025long

Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowledge can contain private information that may be leaked when answering queries, and estimating this privacy leakage is not…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗