3️⃣ The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation Project (Main) -
aclanthology.org/2025.acl-lo...

July 29 Hall 4/5 10:30-12:00

Collab with folks from UP Diliman

#ACL2025 #ACL2025NLP

2️⃣ M-RewardBench: Evaluating Reward Models in Multilingual Settings (Main) - aclanthology.org/2025.acl-lo...

July 28 Hall 4/5 11:00-12:30

Collab with folks from @cohereforai.bsky.social

#ACL2025 #ACL2025NLP

1️⃣ Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback (Main) - aclanthology.org/2025.acl-lo...

7/29 Hall 4/5 10:30-12:00

My project here at @ai2.bsky.social!

#ACL2025NLP

I'll be at @aclmeeting.bsky.social‬ in Vienna! I'm going to present the ff first/co-first author works:

The synthetic preference pipeline was a nice research (and engineering!) challenge: we ablated Ultrafeedback to figure out parts that made it awesome, and made changes such as the inclusion of on-policy data, source of prompts, and many other things.