Marcel Zalmanovici

Publications

• Evaluating perturbation robustness of generative systems that use COBOL code inputs

  • • Samuel Ackerman
    • Wesam Ibraheem
    • et al.
  • 2026
  • ICSE 2026

  Workshop paper

• PACIFIC: a framework for generating benchmarks to check Precise Automatically Checked Instruction Following In Code

  • • Itay Dreyfuss
    • Antonio Abu Nassar
    • et al.
  • 2026
  • ICSE 2026

  Workshop paper

• Exploring Straightforward Methods for Automatic Conversational Red-Teaming

  • • George Kour
    • Naama Zwerdling
    • et al.
  • 2025
  • NAACL 2025

  Conference paper

• Unveiling Safety Vulnerabilities of Large Language Models

  • • George Kour
    • Marcel Zalmanovici
    • et al.
  • 2023
  • EMNLP 2023

  Workshop paper

• High-quality conversational systems

  • • Samuel Ackerman
    • Ateret Anaby-Tavor
    • et al.
  • 2022
  • arXiv

  Paper

• Classifier Data Quality: A Geometric Complexity Based Method for Automated Baseline And Insights Generation

  • • George Kour
    • Marcel Zalmanovici
    • et al.
  • 2022
  • AAAI 2022

  Workshop paper

• Density-based interpretable hypercube region partitioning for mixed numeric and categorical data

  • • Samuel Ackerman
    • Eitan Farchi
    • et al.
  • 2021
  • JSM 2021

  Conference paper

• Machine Learning Model Drift Detection Via Weak Data Slices

  • • Samuel Ackerman
    • Parijat Dube
    • et al.
  • 2021
  • ICSE 2021

  Workshop paper

• FreaAI: Automated extraction of data slices to test machine learning models

  • • Samuel Ackerman
    • Orna Raz
    • et al.
  • 2020
  • AAAI 2020

  Workshop paper

• Detection of data 'drift' over time affecting ML model performance

  • • Samuel Ackerman
    • Orna Raz
    • et al.
  • 2019
  • ISA Annual Meeting 2019

  Invited talk