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…
q-fin.CP2025
SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
Huopu Zhang, Yanguang Liu, Miao Zhang +2
Predicting earnings surprises from financial documents, such as earnings conference calls, regulatory filings, and financial news, has become increasingly important in financial ec…
cs.LG2025
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…