Major Awards
-
Rothschild Fellow
-
Offered Fullbright Fellowship
-
Blavatnik Award for exceptional PhDs
-
KLA (2020, 2021, 2022) scholarship for academic achievement and excellence
-
Clore Scholars Programme scholarship for outstanding researchers pursuing PhD
-
M.A. Valedictorian and best thesis award
-
B.A Summa Cum Laude
Full list: Semantic | Google Scholar Twitter: @LChoshen 🧵s
Chosen Choshen Publications
-
TextArena [play][use][paper] L Guertler, B Cheng, S Yu, B Liu, L Choshen, C Tan
-
BabyLM findings [1][2][Memory and Cognition Journal][site]
-
Pretraining Language Models for Diachronic Linguistic Change Discovery E Fittschen, S Li, T Lippincott, L Choshen, C Messner
-
The Future of Open Human Feedback Shachar Don-Yehia, [long list], Leshem Choshen (Nature Machine Intelligence)
[pdf][ArXiv] -
Zipnn: Lossless compression for AI models M Hershcovitch, A Wood, L Choshen, ... Danny Harnik (IEEE cloud)
-
Model merging with SVD to tie the Knots G Stoica, P Ramesh, B Ecsedi, L Choshen, J Hoffman (ICLR)
-
A Hitchhiker's Guide to Scaling Law Estimation L Choshen, Y Zhang, J Andreas (ICML)
-
tinyBenchmarks: evaluating LLMs with fewer examples FM Polo, L Weber, L Choshen, Y Sun, G Xu, M Yurochkin (ICML)
[bib][pdf][data][Latex] -
Ties-merging: Resolving interference when merging models P Yadav, D Tam, L Choshen, CA Raffel, M Bansal (NeurIPS)
[bib][pdf][code][Latex] -
Genie: Achieving human parity in content-grounded datasets generation A Yehudai, B Carmeli, Y Mass, O Arviv, N Mills, A Toledo, E Shnarch, L Choshen (ICLR)
-
[bib][pdf][code][Latex]
-
Learning from Naturally Occurring Feedback S Don-Yehiya, L Choshen, O Abend
-
ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning Shachar Don-Yehia, Elad Venezian, Colin Raffel, Noam Slonim, Yoav Katz, Leshem Choshen (ACL2023)
[bib][pdf][model][Latex] -
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering Ella Neeman, Roee Aharoni, Or Honovich, Leshem Choshen, Idan Szpektor, Omri Abend (ACL AC Best paper)
[bib][pdf][code][Latex][site] -
Where to start? Analyzing the potential value of intermediate models Leshem Choshen, Elad Venezian, Shachar Don-Yehia, Noam Slonim, Yoav Katz
[bib][pdf][code][Latex][site] -
Fusing finetuned models for better pretraining Leshem Choshen, Elad Venezian, Noam Slonim, Yoav Katz
[bib][pdf][code][Latex] -
The Grammar-Learning Trajectories of Neural Language Models Leshem Choshen, Guy Hacohen, Daphna Weinshall, Omri Abend (ACL2022)
[bib][pdf][code][Latex] -
Project Debater - an Autonomous Debating System (Nature 2021 cover)
[bib][pdf][code][Latex -
Enhancing the Transformer Decoder with Transition-based Syntax Leshem Choshen, Omri Abend (CoNLL 2022)
[bib][pdf][code][Latex] -
On the Weaknesses of Reinforcement Learning for Neural Machine Translation Leshem Choshen, Lior Fox, Zohar Aizenbud, Omri Abend (ICLR 2020)
[bib] [pdf] [code] [Latex] -
Corpus wide argument mining - a working solution Liat Ein-Dor, Eyal Shnarch, Lena Dankin, Alon Halfon, Benjamin Sznajder, Ariel Gera, Carlos Alzate, Martin Gleize, Leshem Choshen, Yufang Hou, Yonatan Bilu, Ranit Aharonov, Noam Slonim (AAAI 2020)
[bib] [pdf] [code] [Latex] -
Leshem Choshen & Omri Abend (ACL 2018) Inherent Biases in Reference-based Evaluation for Grammatical Error Correction and Text Simplification
[bib] [pdf] [code] [Latex] -
Leshem Choshen, Lior Fox, Yonatan Loewenstein (ICLR 2018) DORA The Explorer: Directed Outreaching Reinforcement Action-Selection
[bib] [pdf] [code] [Latex] -
Leshem Choshen & Omri Abend (NAACL-HLT 2018) Reference-less Measure of Faithfulness for Grammatical Error Correction
[bib] [pdf] [code] [Latex]
Errata
-
Automatic Metric Validation for Grammatical Error Correction - Alignment is node alignment and not edge alignment. It is equivalent up to the top nodes of the DAG which should be aligned with each other.