Alert button
Picture for Leshem Choshen

Leshem Choshen

Alert button

Asymmetry in Low-Rank Adapters of Foundation Models

Feb 27, 2024
Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi, Haitz Sáez de Ocáriz Borde, Rickard Brüel Gabrielsson, Leshem Choshen, Marzyeh Ghassemi, Mikhail Yurochkin, Justin Solomon

Viaarxiv icon

tinyBenchmarks: evaluating LLMs with fewer examples

Feb 22, 2024
Felipe Maia Polo, Lucas Weber, Leshem Choshen, Yuekai Sun, Gongjun Xu, Mikhail Yurochkin

Viaarxiv icon

Label-Efficient Model Selection for Text Generation

Feb 12, 2024
Shir Ashury-Tahan, Benjamin Sznajder, Leshem Choshen, Liat Ein-Dor, Eyal Shnarch, Ariel Gera

Viaarxiv icon

Genie: Achieving Human Parity in Content-Grounded Datasets Generation

Jan 25, 2024
Asaf Yehudai, Boaz Carmeli, Yosi Mass, Ofir Arviv, Nathaniel Mills, Assaf Toledo, Eyal Shnarch, Leshem Choshen

Viaarxiv icon

Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI

Jan 25, 2024
Elron Bandel, Yotam Perlitz, Elad Venezian, Roni Friedman-Melamed, Ofir Arviv, Matan Orbach, Shachar Don-Yehyia, Dafna Sheinwald, Ariel Gera, Leshem Choshen, Michal Shmueli-Scheuer, Yoav Katz

Viaarxiv icon

Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability

Jan 16, 2024
Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen, Derry Wijaya, Jacob Andreas

Viaarxiv icon

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization

Nov 22, 2023
Prateek Yadav, Leshem Choshen, Colin Raffel, Mohit Bansal

Viaarxiv icon

Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney

Nov 20, 2023
Shachar Don-Yehiya, Leshem Choshen, Omri Abend

Figure 1 for Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney
Figure 2 for Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney
Figure 3 for Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney
Figure 4 for Human Learning by Model Feedback: The Dynamics of Iterative Prompting with Midjourney
Viaarxiv icon

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion

Nov 13, 2023
Kerem Zaman, Leshem Choshen, Shashank Srivastava

Viaarxiv icon

Efficient Benchmarking (of Language Models)

Aug 31, 2023
Yotam Perlitz, Elron Bandel, Ariel Gera, Ofir Arviv, Liat Ein-Dor, Eyal Shnarch, Noam Slonim, Michal Shmueli-Scheuer, Leshem Choshen

Figure 1 for Efficient Benchmarking (of Language Models)
Figure 2 for Efficient Benchmarking (of Language Models)
Figure 3 for Efficient Benchmarking (of Language Models)
Figure 4 for Efficient Benchmarking (of Language Models)
Viaarxiv icon