4 papers · 1 filter
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
Zirui He, Mingyu Jin, Bo Shen +3
Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging…
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…
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
Haiyan Zhao, Heng Zhao, Bo Shen +3
Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is…
Towards Uncovering How Large Language Model Works: An Explainability Perspective
Haiyan Zhao, Fan Yang, Bo Shen +2
Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opa…