7 papers
Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders
Xu Wang, Yan Hu, Benyou Wang +1
Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavio…
Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization
Zhengzhao Lai, Youbin Zheng, Zhenyang Cai +5
Materials characterization is fundamental to acquiring materials information, revealing the processing-microstructure-property relationships that guide material design and optimiza…
Model Unlearning via Sparse Autoencoder Subspace Guided Projections
Xu Wang, Zihao Li, Benyou Wang +2
Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing…
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
Xu Wang, Yan Hu, Wenyu Du +3
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth i…
TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
Yuzhe Yang, Yifei Zhang, Minghao Wu +5
The study of social emergence has long been a central focus in social science. Traditional modeling approaches, such as rule-based Agent-Based Models (ABMs), struggle to capture th…
Federated Linear Dueling Bandits
Xuhan Huang, Yan Hu, Zhiyan Li +3
Contextual linear dueling bandits have recently garnered significant attention due to their widespread applications in important domains such as recommender systems and large langu…