Add ToM benchmark adapters and sync uma with upstream

[umamogus69]

Updated 'uma' branch on lm-evaluation-harness and pushed changes

Changes made:

• ToMChallenges adapter
• ToMATO adapter alignment with original MCQ protocol
• PersuasiveToM parity fixes
• local uma changes rebased/synced onto the current upstream state

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ umamogus69
❌ hnmarkin
_{You have signed the CLA already but the status is still pending? Let us recheck it.}