William Jurayj
@williamjurayj.bsky.social
PhD student at Johns Hopkins CLSP (@jhuclsp.bsky.social).
Researching natural and formal language processing.
williamjurayj.com
Researching natural and formal language processing.
williamjurayj.com
Pinned
William Jurayj
@williamjurayj.bsky.social
· Feb 20
🚨 You are only evaluating a slice of your test-time scaling model's performance! 🚨
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
Reposted by William Jurayj
JHU computer scientists including @williamjurayj.bsky.social propose a method that allows #AI models to spend more time thinking through problems & uses a confidence score to determine when the AI should say "I don't know" rather than risking a wrong answer, which is crucial for high-stakes domains.
Teaching AI to admit uncertainty
Johns Hopkins researchers show how different "odds" can teach AI models to admit when they're not confident enough in an answer
hub.jhu.edu
July 2, 2025 at 6:59 PM
JHU computer scientists including @williamjurayj.bsky.social propose a method that allows #AI models to spend more time thinking through problems & uses a confidence score to determine when the AI should say "I don't know" rather than risking a wrong answer, which is crucial for high-stakes domains.
Reposted by William Jurayj
You can't just be right, you have to know you're right. Good advice for LLMs, according to new Johns Hopkins research. Sometimes no answer is better than a wrong one - life or death choices in medicine, for example, or big financial decisions. 🧵
March 19, 2025 at 5:27 PM
You can't just be right, you have to know you're right. Good advice for LLMs, according to new Johns Hopkins research. Sometimes no answer is better than a wrong one - life or death choices in medicine, for example, or big financial decisions. 🧵
🚨 You are only evaluating a slice of your test-time scaling model's performance! 🚨
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
February 20, 2025 at 3:14 PM
🚨 You are only evaluating a slice of your test-time scaling model's performance! 🚨
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
📈 We consider how models’ confidence in their answers changes as test-time compute increases. Reasoning longer helps models answer more confidently!
📝: arxiv.org/abs/2502.13962
I’d say a key factor is whether a person’s put in a good faith effort to be right for the right reasons. But I’m to other explanations!
Had a good conversation about "What exactly is misinformation?" with
@williamjurayj.bsky.social
Thread below
@williamjurayj.bsky.social
Thread below
December 6, 2024 at 8:10 PM
I’d say a key factor is whether a person’s put in a good faith effort to be right for the right reasons. But I’m to other explanations!
Reposted by William Jurayj
I noticed a lot of starter packs skewed towards faculty/industry, so I made one of just NLP & ML students: go.bsky.app/vju2ux
Students do different research, go on the job market, and recruit other students. Ping me and I'll add you!
Students do different research, go on the job market, and recruit other students. Ping me and I'll add you!
November 23, 2024 at 7:54 PM
I noticed a lot of starter packs skewed towards faculty/industry, so I made one of just NLP & ML students: go.bsky.app/vju2ux
Students do different research, go on the job market, and recruit other students. Ping me and I'll add you!
Students do different research, go on the job market, and recruit other students. Ping me and I'll add you!