Search Results for author:
Found 2 papers, 1 papers with code
Tradeoffs Between Alignment and Helpfulness in Language Models with Representation Engineering
Second, we show that helpfulness is harmed quadratically with the norm of the representation engineering vector, while the alignment increases linearly with it, indicating a regime in which it is efficient to use representation engineering.
Fundamental Limitations of Alignment in Large Language Models
An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
