Kabir Ahuja
@kabirahuja2431.bsky.social
PhD student @uwnlp.bsky.social
📢 New Paper!
Tired 😴 of reasoning benchmarks full of math & code? In our work we consider the problem of reasoning for plot holes in stories -- inconsistencies in a storyline that break the internal logic or rules of a story’s world 🌎
W @melaniesclar.bsky.social, and @tsvetshop.bsky.social
1/n
Tired 😴 of reasoning benchmarks full of math & code? In our work we consider the problem of reasoning for plot holes in stories -- inconsistencies in a storyline that break the internal logic or rules of a story’s world 🌎
W @melaniesclar.bsky.social, and @tsvetshop.bsky.social
1/n
April 22, 2025 at 6:50 PM
📢 New Paper!
Tired 😴 of reasoning benchmarks full of math & code? In our work we consider the problem of reasoning for plot holes in stories -- inconsistencies in a storyline that break the internal logic or rules of a story’s world 🌎
W @melaniesclar.bsky.social, and @tsvetshop.bsky.social
1/n
Tired 😴 of reasoning benchmarks full of math & code? In our work we consider the problem of reasoning for plot holes in stories -- inconsistencies in a storyline that break the internal logic or rules of a story’s world 🌎
W @melaniesclar.bsky.social, and @tsvetshop.bsky.social
1/n
Reposted by Kabir Ahuja
31% of US adults use generative AI for healthcare 🤯But most AI systems answer questions assertively—even when they don’t have the necessary context. Introducing #MediQ a framework that enables LLMs to recognize uncertainty🤔and ask the right questions❓when info is missing: 🧵
December 6, 2024 at 10:51 PM
31% of US adults use generative AI for healthcare 🤯But most AI systems answer questions assertively—even when they don’t have the necessary context. Introducing #MediQ a framework that enables LLMs to recognize uncertainty🤔and ask the right questions❓when info is missing: 🧵
Reposted by Kabir Ahuja
Excited to release Tulu 3! We worked hard to try and make the best open post-training recipe we could, and the results are good!
I was lucky enough to work on almost every stage of the pipeline in one way or another. Some comments + highlights ⬇️
I was lucky enough to work on almost every stage of the pipeline in one way or another. Some comments + highlights ⬇️
November 21, 2024 at 5:45 PM
Excited to release Tulu 3! We worked hard to try and make the best open post-training recipe we could, and the results are good!
I was lucky enough to work on almost every stage of the pipeline in one way or another. Some comments + highlights ⬇️
I was lucky enough to work on almost every stage of the pipeline in one way or another. Some comments + highlights ⬇️