Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
On-the-go Forgetting without Explicit Unlearning via ERASE
Kushal Chakrabarti, Mayank Baranwal
Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalization, and limited scalability. I…
cs.LG2026
Reliability Scales Inversely: Hallucinations Snowball Faster in Bigger Language Models
Kushal Chakrabarti
Bigger language models are less reliable. Across three families, three benchmarks and six rungs, including in-the-wild chat logs, scaling closes the start-of-response knowledge gap…
cs.LG2026
Enhancing Robustness of Federated Learning via Server Learning
Van Sy Mai, Kushal Chakrabarti, Richard J. La +1
This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and…