Research Interests


I'm interested in a variety of topics in machine learning, NLP, and cognitive science. My research focuses on efficient, interpretable, and controllable ways of reasoning in long-horizon complex tasks. On this path, my colleagues and I investigated case studies on latent reasoning, preference alignment, and agents.

During my PhD, I focused on controlling for properties of text (e.g. writing style) during generation. I drew ideas from psycholinguistics by looking at how human memory works, as well as from linguistics models of information organization. My collaborators and I explored the benefits of incorporating 'human-like' retention in challenging generation areas such as style-transfer, summarization of highly technical texts, and text simplification.

Previously, I worked in developing universal language tools, i.e. tools that would require little to no language-specific tuning. These tools were tested for Quechua and Shipibo-Konibo, native languages of Peru, and have been used ever since to facilitate annotation of linguistic resources in these languages.

Publications & Poster sessions


  • Sparsepo: Controlling preference alignment of llms via sparse token masks
    F. Christopoulou, R.A. Cardenas, G. Lampouras, H. Bou-Ammar, and J. Wang. 2024. [pdf][code]
  • On the Trade-off between Redundancy and Cohesiveness in Summarization
    R.A. Cardenas, S.B. Cohen, and M. Galle. 2024. [pdf]
  • Keep it Together': Enforcing Cohesion in Extractive Summaries by Simulating Human Memory
    R.A. Cardenas, S.B. Cohen, and M. Galle. 2023. [pdf]
  • ‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalism
    R.A. Cardenas, B. Yao, D. Wang, and Y. Hou. Proceedings of EMNLP 2023. [pdf][code][dataset]
  • Unsupervised Extractive Summarization by Human Memory Simulation
    R.A. Cardenas, S.B. Cohen, and M. Galle. 2021. [pdf]
  • Universal Morphological Analysis using Reinforcement Learning
    R.A. Cardenas Masters Thesis. Charles University in Prague, 2019. [pdf][code]
  • Morphological Process Transduction: Towards interpretable multi-lingual morphological analysis
    R.A. Cardenas Masters Thesis. University of Malta, 2019. [pdf][code]
  • CUNI–Malta system at SIGMORPHON 2019 Shared Task on Morphological Analysis and Lemmatization in context: Operation-based word formation
    R.A. Cardenas, Claudia Borg and Daniel Zeman. Processing of SIGMORPHON 2019. [paper][code]
  • A grounded unsupervised universal part-of-speech tagger for low-resource languages
    R.A. Cardenas, Ying Lin, Heng Ji and Jonathan May.
    Proceedings of NAACL 2019. [paper][code]
  • Replacing Linguists with Dummies: A Serious Need for Trivial Baselines in Multi-Task Neural Machine Translation
    Daniel Kondratyuk, R.A. Cardenas and Ondrej Bojar.
    Proceedings of The Prague Bulletin of Mathematical Linguists, volume 113. [pdf]
  • A Morphological Analyzer for Shipibo-Konibo
    R.A. Cardenas and Daniel Zemman.
    Proceedings of the 15th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, 2018. [pdf][code]
  • Siminchik: A Speech Corpus for Preservation of Southern Quechua
    R.A. Cardenas, R. Zevallos, R. Baquerizo, L. Camacho.
    Proceedings of the 2nd Workshop on Improving Social Inclusion using NLP, co-located with LREC 2018. [pdf]
  • Document modeling with external attention for sentence extraction
    S. Narayan, R.A. Cardenas, N. Papasarantopoulos, S.B. Cohen, M. Lapata, J. Yu, Y. Chang.
    Proceedings of the 56th Annual Meeting of the ACL (Long Papers), 2018. [pdf][code]
  • Improving Topic Coherence Using Entity Extraction Denoising
    R.A. Cardenas, K.S. Bello, A.R. Valle, E.R. Villota and A.M. Coronado.
    The Prague Bulletin of Mathematical Linguistics 110.1 (2018): 85-101. [pdf][code]
  • Panorama of the market demand for Mechanical Engineers in South American countries
    R.A. Cardenas, K.S. Bello, A.R. Valle, E.R. Villota and A.M. Coronado.
    Proceedings of ASME 2015 International Mechanical Engineering Congress & Exposition (IMECE 2015). [pdf]
  • Labor market demand analysis for engineering majors in Peru using Shallow Parsing and Topic Modeling.
    R.A. Cardenas, K.S. Bello and A.M. Coronado.
    Machine Learning Summer School Poster Session, Kyoto, Japan, August, 2015. [pdf, poster]
  • Peruvian labor market demand analysis for Mechanical and Electrical Engineering
    K.S.Bello, R.A.Cardenas, A.R.Valle, E.R.Villota and A.M.Coronado.
    Proceedings of XXI CONIMERA, Huancayo, Peru, August, 2015. [pdf]