2 citations · 2 across the 2 of their papers we have counts for
2 papers
cs.AI2024
WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs
Eryk Banatt, Jonathan Cheng, Skanda Vaidyanath +1
While large language models have shown impressive capabilities across a wide range of domains, they still encounter significant challenges in reasoning tasks that require gathering…
cs.LG2023★ 2 cited
Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes
Eryk Banatt, Vickram Rajendran, Liam Packer
In practical scenarios, it is often the case that the available training data within the target domain only exist for a limited number of classes, with the remaining classes only a…