67 citations · 217 across the 55 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CL2024★ 1 cited
Spectral Editing of Activations for Large Language Model Alignment
Yifu Qiu, Zheng Zhao, Yftah Ziser +3
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effe…
cs.CL2024
`Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory
Ronald Cardenas, Matthias Galle, Shay B. Cohen
Extractive summaries are usually presented as lists of sentences with no expected cohesion between them. In this paper, we aim to enforce cohesion whilst controlling for informativ…