Joykirat
@joykiratsingh
Incoming CS PhD Student @unc_ai_group @UNC, advised by. @mohitban47 | ex RF @MSFTResearch
I’m thrilled to share that I’ll be joining the University of North Carolina at Chapel Hill for my CS PhD this fall!! 🎓💙 @UNC I’ll be working with the amazing @mohitban47 at @uncnlp. Grateful to everyone who’s supported me, excited for this new chapter! 🚀
Attribution is key to being able to audit an LLM's generations, but is only useful when it is high precision. LAQuer requires models to attribute arbitrary spans in the output to fine-grained source spans, making checking for factuality in the output faster and easier on…
🚨 Introducing LAQuer, accepted to #ACL2025 (main conf)! LAQuer provides more granular attribution for LLM generations: users can just highlight any output fact (top), and get attribution for that input snippet (bottom). This reduces the amount of text the user has to read by 2…
Huge thanks to @_akhaliq for the shoutout to our paper on building a unified framework to teach models how to invoke tools in a multi turn reasoning setup via RL. Further details in the thread: x.com/joykiratsingh/…
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning