1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.LG2024
A Little Confidence Goes a Long Way
John Scoville, Shang Gao, Devanshu Agrawal +1
We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs). Performance is on par with the…
cs.CL2024★ 1 cited
Can't Remember Details in Long Documents? You Need Some R&R
Devanshu Agrawal, Shang Gao, Martin Gajek
Long-context large language models (LLMs) hold promise for tasks such as question-answering (QA) over long documents, but they tend to miss important information in the middle of c…