3 papers
cs.CL2025
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…
cs.CL2025
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…
cs.CL2025
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…