Leshem Choshen

Publications

• LIVEXIV - A MULTI-MODAL LIVE BENCHMARK BASED ON ARXIV PAPERS CONTENT

  • • Nimrod Shabtay
    • Felipe Maia Polo
    • et al.
  • 2025
  • ICLR 2025

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

  • • Prateek Yadav
    • Leshem Choshen
    • et al.
  • 2025
  • TMLR

• A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

  • • Prateek Yadav
    • Colin Raffel
    • et al.
  • 2025
  • TMLR

• Efficient multi-prompt evaluation of LLMs

  • • Felipe Maia Polo
    • Ronald Xu
    • et al.
  • 2024
  • NeurIPS 2024

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

  • • Kerem Zaman
    • Leshem Choshen
    • et al.
  • 2024
  • EMNLP 2024

• NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning

  • • Eliyahu Schwartz
    • Leshem Choshen
    • et al.
  • 2024
  • EMNLP 2024

• Label-Efficient Model Selection for Text Generation

  • • Shir Ashury Tahan
    • Ariel Gera
    • et al.
  • 2024
  • ACL 2024

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

  • • Afra Feyza Akyürek
    • Ekin Akyürek
    • et al.
  • 2024
  • ACL 2024

• Data Contamination Report from the 2024 CONDA Shared Task

  • • Oscar Sainz
    • Iker García-ferrero
    • et al.
  • 2024
  • ACL 2024

• tinyBenchmarks: evaluating LLMs with fewer examples

  • • Felipe Maia Polo
    • Lucas Weber
    • et al.
  • 2024
  • ICML 2024