3 papers
cs.LG2026
Multi-component Causal Tracing in Large Language Models
Zirui Yan, Dennis Wei, Dmitriy A. Katz +2
Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computa…
stat.ML2024
Linear Causal Bandits: Unknown Graph and Soft Interventions
Zirui Yan, Ali Tajer
Designing causal bandit algorithms depends on two central categories of assumptions: (i) the extent of information about the underlying causal graphs and (ii) the extent of informa…
stat.ML2024
Improved Bound for Robust Causal Bandits with Linear Models
Zirui Yan, Arpan Mukherjee, Burak Varıcı +1
This paper investigates the robustness of causal bandits (CBs) in the face of temporal model fluctuations. This setting deviates from the existing literature's widely-adopted assum…