
Harsh Jhamtani
@harsh_jhamtani
Researcher @Microsoft | NLP / ML PhD from @LTIatCMU | Previously at @UCSanDiego @allen_ai @AdobeResearch @facebookai @iitroorkee | Opinions are my own.
ID: 2435694588
https://sites.google.com/view/harshjhamtani/home 09-04-2014 16:42:21
70 Tweet
533 Takipçi
400 Takip Edilen


New Columbia NLP #EMNLP2022 paper where we leverage the strong few-shot capabilities of LLMs 🤖 & evaluative strength of expert humans 🧑💻 to create a benchmark for Figurative Language Understanding with a focus on Explanations (1/n) Paper: arxiv.org/pdf/2205.12404… #NLProc #xAI


Excited to announce a new dataset–– the result of a fun summer with Harsh Jhamtani at Semantic Machines. We present KNUDGE, a dataset of _real_ dialogue trees from The Outer Worlds (The Outer Worlds) with associated biography and quest specifications. nweir127.github.io/assets/papers/…



"Interpreting User Requests in the Context of Natural Language Standing Instructions" to appear in #NAACL2024 Findings Paper: shorturl.at/hsFVZ Data: huggingface.co/datasets/nikit… Code: github.com/nikitacs16/nlsi Patrick Xia Jacob Andreas Jason Eisner Benjamin Van Durme Harsh Jhamtani



“Ontologically Faithful Generation of Non-Player Character Dialogues” Nathaniel Weir, Ryan Thomas, Randolph d'Amore, Kellie Hill, Benjamin Van Durme, Harsh Jhamtani arxiv.org/abs/2212.10618

“Learning to Retrieve Iteratively for In-Context Learning” Yunmo Chen, Tongfei Chen, Harsh Jhamtani,Patrick Xia, Richard Shin, Jason Eisner, Benjamin Van Durme arxiv.org/abs/2406.14739







I am growing an R&D team around Copilot Tuning, a newly announced effort that supports adaptation at a customer-specific level. Join us! jobs.careers.microsoft.com/global/en/job/… We collaborate with a crack team of eng and scientists that support the product, also growing! jobs.careers.microsoft.com/global/en/job/…