Priyanka Kargupta @ EMNLP'24
@pkargupta.bsky.social
structured nlp to help models & humans critically think
nlp phd candidate @UIUC_NLP | nsf grfp fellow
prev: cs'22 @berkeley_ai | @IntelAI | @IBMResearch
nlp phd candidate @UIUC_NLP | nsf grfp fellow
prev: cs'22 @berkeley_ai | @IntelAI | @IBMResearch
hello! would appreciate being added, thank you!
November 26, 2024 at 11:41 AM
hello! would appreciate being added, thank you!
Hello! Would love to be added to this, thank you so much!
November 19, 2024 at 5:28 PM
Hello! Would love to be added to this, thank you so much!
TreeInstruct is preferred 78.43% of the time. It solves 14.09% more bugs across all settings, and our questions are 14.18% better at addressing bugs, maintaining relevance, and ensuring logical conversation flow. TreeInstruct also adapts to human students of varying backgrounds.
November 19, 2024 at 5:23 PM
TreeInstruct is preferred 78.43% of the time. It solves 14.09% more bugs across all settings, and our questions are 14.18% better at addressing bugs, maintaining relevance, and ensuring logical conversation flow. TreeInstruct also adapts to human students of varying backgrounds.
TreeInstruct estimates the knowledge a student needs to debug their code and devises a conversation plan.
It then dynamically constructs a question tree based on its interactions with the student, navigating the knowledge state space till the student comprehends & fixes all misunderstandings &bugs.
It then dynamically constructs a question tree based on its interactions with the student, navigating the knowledge state space till the student comprehends & fixes all misunderstandings &bugs.
November 19, 2024 at 5:23 PM
TreeInstruct estimates the knowledge a student needs to debug their code and devises a conversation plan.
It then dynamically constructs a question tree based on its interactions with the student, navigating the knowledge state space till the student comprehends & fixes all misunderstandings &bugs.
It then dynamically constructs a question tree based on its interactions with the student, navigating the knowledge state space till the student comprehends & fixes all misunderstandings &bugs.
github.com/agarwalishik...
We apply TreeInstruct to code debugging. Prior works directly give away bugs/fixes, assume single-turn conversations, and only work for one bug. We create a realistic, multi-bug dataset, where the bugs can be either mutually independent or dependent.
We apply TreeInstruct to code debugging. Prior works directly give away bugs/fixes, assume single-turn conversations, and only work for one bug. We create a realistic, multi-bug dataset, where the bugs can be either mutually independent or dependent.
November 19, 2024 at 5:23 PM
github.com/agarwalishik...
We apply TreeInstruct to code debugging. Prior works directly give away bugs/fixes, assume single-turn conversations, and only work for one bug. We create a realistic, multi-bug dataset, where the bugs can be either mutually independent or dependent.
We apply TreeInstruct to code debugging. Prior works directly give away bugs/fixes, assume single-turn conversations, and only work for one bug. We create a realistic, multi-bug dataset, where the bugs can be either mutually independent or dependent.