publications

2025

1. 

   Many LLMs Are More Utilitarian Than One

   Razan Baltaji^*, Anita Keshmirian^*, Babak Hemmatian, and 2 more authors

   In Advances in Neural Information Processing Systems, 2025

   Link Bib Code Poster

   @inproceedings{keshmirian2025many,
     title = {Many {LLM}s Are More Utilitarian Than One},
     author = {Baltaji, Razan and Keshmirian, Anita and Hemmatian, Babak and Asghari, Hadi and Varshney, Lav R.},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2025},
     url = {https://openreview.net/forum?id=wn3VBRz5GK},
   }

2. 

   Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study

   Razan Baltaji, Saurabh Pujar, Martin Hirzel, and 3 more authors

   Transactions on Machine Learning Research, 2025

   Link Bib Code

   @article{baltaji2025crosslingual,
     title = {Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study},
     author = {Baltaji, Razan and Pujar, Saurabh and Hirzel, Martin and Mandel, Louis and Buratti, Luca and Varshney, Lav R.},
     journal = {Transactions on Machine Learning Research},
     issn = {2835-8856},
     year = {2025},
     url = {https://openreview.net/forum?id=1PRBHKgQVM},
   }

2024

1. 

   Conformity, Confabulation, and Impersonation: Persona Inconstancy in Multi-Agent LLM Collaboration

   Razan Baltaji, Babak Hemmatian, and Lav Varshney

   In Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP, 2024

   Link Bib Code Poster

   @inproceedings{baltaji-etal-2024-conformity,
     title = {Conformity, Confabulation, and Impersonation: Persona Inconstancy in Multi-Agent {LLM} Collaboration},
     author = {Baltaji, Razan and Hemmatian, Babak and Varshney, Lav},
     booktitle = {Proceedings of the 2nd Workshop on Cross-Cultural Considerations in NLP},
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.c3nlp-1.2/},
     pages = {17--31},
   }

2. 

   Efficient Model-Agnostic Multi-Group Equivariant Networks

   Razan Baltaji^*, Sourya Basu^*, and Lav R. Varshney

   Transactions on Machine Learning Research, 2024

   Link Bib Code

   @article{baltaji2024efficient,
     title = {Efficient Model-Agnostic Multi-Group Equivariant Networks},
     author = {Baltaji, Razan and Basu, Sourya and Varshney, Lav R.},
     journal = {Transactions on Machine Learning Research},
     issn = {2835-8856},
     year = {2024},
     url = {https://openreview.net/forum?id=HCMDtc0ZhV},
   }

2023

1. 

   Probing Numeracy and Logic of Language Models of Code

   Razan Baltaji and Parth Thakkar

   In 2023 IEEE/ACM International Workshop on Interpretability and Robustness in Neural Software Engineering (InteNSE), 2023

   Link Bib

   @inproceedings{baltaji2023probing,
     author = {Baltaji, Razan and Thakkar, Parth},
     booktitle = {2023 IEEE/ACM International Workshop on Interpretability and Robustness in Neural Software Engineering (InteNSE)},
     title = {Probing Numeracy and Logic of Language Models of Code},
     year = {2023},
     pages = {8--13},
     url = {https://ieeexplore.ieee.org/document/10189046},
     keywords = {interpretability, probing, language models for source code},
   }