N
Nikhil Mehta
Researcher at Purdue University
Publications - 6
Citations - 24
Nikhil Mehta is an academic researcher from Purdue University. The author has contributed to research in topics: Computer science & Blocks world. The author has an hindex of 2, co-authored 2 publications receiving 6 citations.
Papers
More filters
Proceedings ArticleDOI
Tackling Fake News Detection by Continually Improving Social Context Representations using Graph Neural Networks
TL;DR: Inference operators are formulated which augment the graph edges by revealing unobserved interactions between its elements, such as similarity between documents’ contents and users’ engagement patterns, resulting in improved performance in fake news detection experiments.
Proceedings ArticleDOI
Improving Natural Language Interaction with Robots Using Advice
Nikhil Mehta,Dan Goldwasser +1 more
TL;DR: This paper suggests a protocol for including advice, high-level observations about the task, which can help constrain the agent’s prediction, and explores model self-generated advice which can still improve results.
Journal ArticleDOI
Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
Wang-Cheng Kang,Jianmo Ni,Nikhil Mehta,Maheswaran Sathiamoorthy,Lichan Hong,Ed H. Chi,Derek Zhiyuan Cheng +6 more
TL;DR: In this paper , the authors conduct a thorough examination of both collaborative filtering and large language models within the classic task of user rating prediction, which involves predicting a user's rating for a candidate item based on their past ratings.
Posted Content
Improving Natural Language Interaction with Robots Using Advice
Nikhil Mehta,Dan Goldwasser +1 more
TL;DR: This paper proposed a protocol for including advice, high-level observations about the task, which can help constrain the agent's prediction, and showed that even simple advice can help lead to significant performance improvements.
Journal ArticleDOI
Better Generalization with Semantic IDs: A case study in Ranking for Recommendations
Anima Singh,Trung Vu,Raghunandan H. Keshavan,Nikhil Mehta,Xinyang Yi,Lichan Hong,Lukasz Andrzej Heldt,Li Wei,Ed H. Chi,Maheswaran Sathiamoorthy +9 more
TL;DR: In this article , the authors use semantic IDs, a compact discrete item representations learned from content embeddings using RQ-VAE that captures hierarchy of concepts in items, as a replacement of item IDs in a resource-constrained ranking model.