About me
Hi, I’m Alireza Salemi (علیرضا سالمی) [CV].
I am a second-year Ph.D. student at the Manning College of Information and Computer Sciences in University of Massachusetts Amherst. I am working at the Center for Intelligent Information Retrieval under the supervision of Hamed Zamani. I am also a part-time Student Researcher at Google Research, working on personalizing LLMs. Previously, I was a B.Sc. student at the school of electrical and computer engineering in University of Tehran, where I worked on natural language processing under the supervision of Azadeh Shakery.
My research interests lie in natural language processing and machine learning when they meet information retrieval, i.e., retrieval-enhanced machine learning (a.k.a, RAG). Recently, I have been working on personalizing large language models, multi-modal information retrieval, multi-modal knowledge grounding, and designing a search engine for all RAG LLMs (like Google for LLMs but tailored to their needs)! Previously, I worked on text summarization, translation, and hate speech detection.
News
2024.7: I am honored to receive “The Best Short Paper Award” at SIGIR 2024 for our paper, “Evaluating Retrieval Quality in Retrieval-Augmented Generation.”
2024.6: I started as a Student Researcher at Google Research to work on personalizing LLMs!
2024.5: Our paper, “LaMP: When Large Language Models Meet Personalization” about personalizing large language models got accepted to ACL 2024 main conference!
2024.3: 3 papers got accepted to SIGIR 2024! Look at my publications for details!
2023.7: I am honored to receive “The Best Student Paper Award” at SIGIR 2023 for our paper, “A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering.”
2023.6: Our paper, “Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering” has been accepted at ICTIR 2023.
2023.5: I am honored to receive the “W. Bruce Croft Graduate Scholarship” for my research.
2023.4: Checkout our new pre-print, “LaMP: When Large Language Models Meet Personalization” about personalizing large language models!
2023.4: Our paper, “A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering” has been accepted as a long paper for SIGIR 2023.
2022.9: Started my Ph.D. at the University of Massachusetts Amherst!
2021.10: Strated my job as NLP data scientist at Sotoon!
2021.9: I got the Best Thesis Award in Computer Engineering for my B.Sc. thesis!
- 2021.8: Our long paper entitled “ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization” has been accepted as a long paper for the main conference of EMNLP 2021!
- 2021.8: I have defended my bachelor thesis about language modeling and summarization.
- 2021.8: Our paper entitled “UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models” has been published in SemEval 2021.
