4 papers
PRISM Edit: One Vector for All Temporal Answers
Chen Huang, Qi Zheng, Ruiqin Zheng +2
The paper proposes PRISM Edit, a method that updates large language models to handle changing temporal facts by learning a single representation that can be modulated for different…
Do Language Models Use Their Depth Efficiently?
Róbert Csordás, Christopher D. Manning, Christopher Potts
Modern LLMs are increasingly deep, and depth correlates with performance, albeit with diminishing returns. However, do these models use their depth efficiently? Do they compose mor…
Improved Representation Steering for Language Models
Zhengxuan Wu, Qinan Yu, Aryaman Arora +2
Steering methods for language models (LMs) seek to provide fine-grained and interpretable control over model generations by variously changing model inputs, weights, or representat…
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Zhengxuan Wu, Aryaman Arora, Atticus Geiger +5
Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability resea…