Ori Ram
Research Scientist


I'm a Research Scientist at Google Research, where I work mainly on natural language processing and large language models (LMs).
I'm mostly excited about making LMs more factual.

Prior to coming to Google, I obtained my PhD from Tel Aviv University.
I was fortunate to be advised by Amir Globerson and to collaborate closely with Jonathan Berant and Omer Levy.

I was also a Research Scientist at AI21 Labs in 2018-2024. 


In-Context Retrieval-Augmented Language Models
Ori Ram*, Yoav Levine*, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham
TACL 2023
Paper   Code

What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary
Ori Ram,  Liat Bezalel, Adi Zicher, Yonatan Belinkov, Jonathan Berant, Amir Globerson
ACL 2023 (Oral)

Making Retrieval-Augmented Language Models Robust to Irrelevant Context
Ori Yoran, Tomer Wolfson, Ori Ram, Jonathan Berant
ICLR 2024
Paper   Code 

Generating Benchmarks for Factuality Evaluation of Language Models
Dor Muhlgay, Ori Ram, Inbal Magar, Yoav Levine, Nir Ratner, Yonatan Belinkov, Omri Abend, Kevin Leyton-Brown, Amnon Shashua, Yoav Shoham
EACL 2024
Paper   Code 

Learning to Retrieve Passages without Supervision
Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson
NAACL 2022 (Oral)
Paper   Code   Models   Blog (Weaviate)   Podcast (Weaviate)    Podcast (Neural IR Talks)   Cite     

Parallel Context Windows Improve In-Context Learning of Large Language Models
Nir Ratner, Yoav Levine, Yonatan Belinkov, Ori Ram, Omri Abend, Ehud Karpas, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham
ACL 2023
Paper   Code

Standing on  the Shoulders of Giant Frozen Language Models
Yoav Levine, Itay Dalmedigos, Ori Ram, Yoel Zeldes, Daniel Jannai, Dor Muhlgay, Yoni Osin, Opher Lieber, Barak Lenz, Shai Shalev-Shwartz, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham

Transformer Language Models without Positional Encodings Still Learn Positional Information
Adi Haviv, Ori Ram, Ofir Press, Peter Izsak, Omer Levy
EMNLP 2022 (Findings)

Few-Shot Question Answering by Pretraining Span Selection
Ori Ram*, Yuval Kirstain*, Jonathan Berant, Amir Globerson, Omer Levy
ACL 2021 (Oral)
Paper   Code   Models   Cite

How Optimal is Greedy Decoding for Extractive Question Answering?
Or Castel, Ori Ram, Avia Efrat, Omer Levy
AKBC 2022 (Oral)
Paper   Code   Models   Cite

Coreference Resolution without Span Representations
Yuval Kirstain*, Ori Ram*, Omer Levy
ACL 2021 (Oral)
Paper   Code & Model   Cite

SenseBERT: Driving Some Sense into BERT
Yoav Levine, Barak Lenz, Or Dagan, Ori Ram, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham
ACL 2020
Paper   Cite

Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
Tal Schuster*, Ori Ram*, Regina Barzilay, Amir Globerson
NAACL 2019 (Oral)
Paper   Code & Models   Cite