16 citations · 28 across the 11 of their papers we have counts for
4 papers · 1 filter
KnowThyself: An Agentic Assistant for LLM Interpretability
Suraj Prasai, Mengnan Du, Ying Zhang +1
We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intens…
Rep2Text: Decoding Full Text from a Single LLM Token Representation
Haiyan Zhao, Zirui He, Yiming Tang +4
Large language models represent text as hidden numerical patterns, but what information these representations actually contain remains a mystery. Can we recover the original text f…
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Haiyan Zhao, Xuansheng Wu, Fan Yang +3
Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder…
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
Zirui He, Haiyan Zhao, Yiran Qiao +4
The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper p…