11 citations · 24 across the 10 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023★ 4 cited
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
Suhas Kotha, Jacob Mitchell Springer, Aditi Raghunathan
We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outsi…
cs.LG2023★ 7 cited
Provably Bounding Neural Network Preimages
Suhas Kotha, Christopher Brix, Zico Kolter +2
Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a…