Undergrad researcher at UT Austin, interested in NLP https://victorwang37.github.io/https://bsky.app/profile/victorwang37.bsky.socialhttps://bsky.app/profile/victorwang37.bsky.social/post/3ljppjvstjk2kLLM judges have become ubiquitous, but valuable signal is often ignored at inference. We analyze design decisions for leveraging judgment distributions from LLM-as-a-judge: 🧵 (w/ Michael J.Q. Zhang, @eunsol.bsky.social)06 Mar 2025 14:32 +0000at://did:plc:uoc3ehbbwa65hfppglahf2km/app.bsky.feed.post/3ljppjvstjk2k