Publications

Please check my Google Scholar page for the latest updates.

2026

  1. Personalized Benchmarking: Evaluating LLMs by Individual Preferences
    Cristina Gârbacea, Heran Wang, and Chenhao Tan
    arXiv preprint arXiv:2604.18943, 2026
    arXiv

2025

  1. Hyperalign: Interpretable Personalized LLM Alignment via Hypothesis Generation
    Cristina Gârbacea and Chenhao Tan
    arXiv preprint arXiv:2505.00038, 2025
    arXiv
  2. Evaluating the Goal-Directedness of Large Language Models
    Tom Everitt *, Cristina Gârbacea *, Alexis Bellot, and 4 more authors
    arXiv preprint arXiv:2504.11844, 2025
    arXiv
  3. Why is Constrained Neural Language Generation Particularly Challenging?
    Cristina Gârbacea and Qiaozhu Mei
    Transactions on Machine Learning Research, 2025
    arXiv PDF
  4. RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
    David Reber, Sean M Richardson, Todd Nief, and 2 more authors
    In Forty-second International Conference on Machine Learning, 2025
    arXiv PDF

2024

  1. Bonbon Alignment for Large Language Models and the Sweetness of Best-of-N Sampling
    Lin Gui, Cristina Gârbacea, and Victor Veitch
    Advances in Neural Information Processing Systems, 2024
    arXiv PDF

2023

  1. Neural language generation for content adaptation: Explainable, efficient low-resource text simplification and evaluation
    Georgeta-Cristina Gârbacea
    University of Michigan, 2023
    PDF
  2. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
    Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, and 8 more authors
    Transactions on machine learning research, 2023
    arXiv PDF
  3. What’s your Use Case? A Taxonomy of Causal Evaluations of Post-hoc Interpretability
    David Reber, Cristina Gârbacea, and Victor Veitch
    In Causal Representation Learning Workshop at NeurIPS 2023, 2023
    PDF

2022

  1. GEM v2: Multilingual NLG benchmarking in a single line of code
    Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, and 8 more authors
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2022
    PDF
  2. Adapting pre-trained language models to low-resource text simplification: The path matters
    Cristina Gârbacea and Qiaozhu Mei
    In Conference on Lifelong Learning Agents, 2022
    PDF Poster Slides
  3. Speech coding using content latent embedding vectors and speaker latent embedding vectors
    Cristina Gârbacea, Aaron Gerard Antonius Oord, Yazhe Li, and 4 more authors
    2022
    US Patent 11,257,507
    PDF

2021

  1. The GEM benchmark: Natural language generation, its evaluation and metrics
    Sebastian Gehrmann, Tosin Adewumi, Karmanya Aggarwal, and 8 more authors
    In Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021), 2021
    PDF
  2. Explainable prediction of text complexity: The missing preliminaries for text simplification
    Cristina Gârbacea, Mengtian Guo, Samuel Carton, and 1 more author
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021
    PDF Poster Slides

2020

  1. Neural language generation: Formulation, methods, and evaluation
    Cristina Gârbacea and Qiaozhu Mei
    arXiv preprint arXiv:2007.15780, 2020
    arXiv
  2. UMSIForeseer at SemEval-2020 Task 11: Propaganda detection by fine-tuning BERT with resampling and ensemble learning
    Yunzhe Jiang, Cristina Gârbacea, and Qiaozhu Mei
    In Proceedings of the Fourteenth Workshop on Semantic Evaluation, 2020
    PDF

2019

  1. Low bit-rate speech coding with VQ-VAE and a WaveNet decoder
    Cristina Gârbacea, Aäron Oord, Yazhe Li, and 4 more authors
    In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
    PDF Poster
  2. Judge the judges: A large-scale evaluation study of neural language models for online review generation
    Cristina Gârbacea, Samuel Carton, Shiyan Yan, and 1 more author
    In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019
    PDF Poster

2017

  1. A Systematic Analysis of Sentence Update Detection for Temporal Summarization
    Cristina Gârbacea and Evangelos Kanoulas
    In European Conference on Information Retrieval, 2017
    PDF

2016

  1. Temporal Summarization of News Streams
    Georgeta-Cristina Gârbacea
    University of Amsterdam, 2016

2015

  1. Supporting exploration of historical perspectives across collections
    Daan Odijk, Cristina Gârbacea, Thomas Schoegje, and 4 more authors
    In International Conference on Theory and Practice of Digital Libraries, 2015
    PDF
  2. Combining Multiple Signals for Semanticizing Tweets: University of Amsterdam at# Microposts2015.
    Cristina Gârbacea, Daan Odijk, David Graus, and 3 more authors
    In # MSM, 2015
    PDF
  3. The University of Amsterdam (ILPS. UvA) at TREC 2015 Temporal Summarization Track.
    Cristina Gârbacea, Evangelos Kanoulas, and others
    In TREC, 2015
    PDF

2014

  1. Detecting the Reputation Polarity of Microblog Posts.
    Cristina Gârbacea, Manos Tsagkias, and Maarten Rijke
    In ECAI, 2014
    PDF
  2. Feature Selection and Data Sampling Methods for Learning Reputation Dimensions.
    Cristina Gârbacea, Manos Tsagkias, and Maarten Rijke
    In CLEF (Working Notes), 2014
    PDF