These settings tell the driver which process to connect to on your Hadoop cluster. Hive Server is the default process and Beeswax is a newer process designed to better support concurrency and provide authentication using Kerberos. The one you pick is determined by what process is running on the Hadoop cluster.
Thanks Logan, I appreciate the response! I was actually wondering more about the pros and cons of using Hive Server vs Beeswax.
Logan essentially answered this: If you wish to have better support for concurrent queries (issued by multiple users connected at a time), as well as support for authentication and data security, you should go with Beeswax.