Karim Saraipour

According to our database, Karim Saraipour authored at least 3 papers in 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Accountability Attribution: Tracing Model Behavior to Training Processes.

Shichang Zhang, Hongzhe Du, Karim Saraipour, Jiaqi W. Ma, Himabindu Lakkaraju

CoRR, June, 2025

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence.

Hongzhe Du, Weikai Li, Min Cai, Karim Saraipour, Zimin Zhang, Himabindu Lakkaraju, Yizhou Sun, Shichang Zhang

CoRR, April, 2025

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits

Karim Saraipour

PhD thesis, 2025