🧑‍🔬 Hamed Zamani

Affiliations

• University of Massachusetts Amherst · Amherst Center, United States — current · 2016–2026 on 148 papers · employment (Wikidata)
• Amherst College · Amherst Center, United States — current · 2026 on 1 paper
• Microsoft (United States) · Redmond, United States — 2020–2024 on 14 papers
• University of Tehran · Tehran, Iran — 2014–2019 on 7 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

Topics

Language models & pretraining2Information retrieval & search1

Papers

The most cited first (OpenAlex and our library).

1. Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning (2025 · 303 citations)
   Large language models often need outside, current knowledge, but simply prompting them to use a search engine works poorly because they were never trained to interact with one.
2. LaMP: When Large Language Models Meet Personalization (2024 · 239 citations)
   Most NLP benchmarks evaluate models the same way for every user, so there has been little infrastructure for studying how LLMs can tailor outputs to individuals.

Also in our library

3 more works of theirs are in our library without a page here yet; they will appear as we publish them.

Co-authors here

3 co-authors with a page, the most papers together first.

• Dong Wang
• Jiawei Han
• Michael Bendersky

Cited by

Papers of our library cite their works 468 times (of the 140 884 papers whose bibliographies we read); 9 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/hamed-zamani/