Publications

[Google Scholar] [DBLP]

• Gemini: a family of highly capable multimodal models [pdf]

Gemini Team, Google

• Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting [pdf]

P. Lahoti, N. Blumm, X. Ma, R. Kotikalapudi, S. Potluri, Q. Tan, H. Srinivasan, B. Packer, A. Beirami, A. Beutel, J. Chen

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing [EMNLP 2023]

• FRAPP\'E: A Post-Processing Framework for Group Fairness Regularization [pdf]

A. Ţifrea, P. Lahoti, B. Packer, Y. Halpern, A. Beirami, F. Prost

• AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications [pdf]|[dataset]

B. Radharapu, K. Robinson, L. Aroyo, P. Lahoti

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track [EMNLP 2023]

• Responsible model deployment via model-agnostic uncertainty learning [pdf]

P. Lahoti, K. P. Gummadi,  G. Weikum 

Machine Learning (2023) 112:939–970

• Detecting and Mitigating Test-time Failure Risks via Model-agnostic Uncertainty Learning [pdf]
  P. Lahoti, K. P. Gummadi, and G. Weikum
  Proceedings of the IEEE International Conference on Data Mining [ICDM 2021] 

• Accounting for Model Uncertainty in Algorithmic Discrimination [pdf]
  J. Ali, P. Lahoti, and K. P. Gummadi
  Proceedings of the AAAI/ACM conference on Artificial Intelligence, Ethics, and Society [AIES 2021]

• Fairness without Demographics through Adversarially Reweighted Learning [pdf]|[code]
  P. Lahoti, A. Beutel, J. Chen, K. Lee, F. Prost, N. Thain, X. Wang, and E. H. Chi
  Advances in Neural Information Processing Systems [NeurIPS 2020]

• Operationalizing Individual Fairness with Pairwise Fair Representationss [pdf]|[code]
  P. Lahoti, K. P. Gummadi, G. Weikum
  Proceedings of the VLDB Endowment Vol. 13 No. 4 [PVLDB 2019]

• An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision [pdf]
  H. Wang, N. Grgic-Hlaca, P. Lahoti, K. P. Gummadi, A. Weller
  Workshop on Human-Centric Machine Learning at NeurIPS 2019 [NeurIPS 2019]

• iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making [pdf]|[ppt]|[code]
  P. Lahoti, K. P. Gummadi, G. Weikum
  Proceedings of the 35th IEEE International Conference on Data Engineering [ICDE 2019]

• Joint Non-negative Matrix Factorization for Learning Ideological Leaning on Twitter [pdf][software]
  P. Lahoti, K. Garimella, A. Gionis
  Proceedings of the 11th ACM International Conference on Web Search and Data Mining [WSDM 2018]

• Finding Topical Experts in Twitter via Query-Dependent Personalized PageRank [pdf]
  P. Lahoti, G. De Francisci Morales, A. Gionis
  Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining [ASONAM 2017]

• Efficient Set Intersection Counting Algorithm for Text Similarity Measures [pdf]
  P. Lahoti, P. K. Nicholson, B. Taneva
  Proceedings of the 19th Workshop on Algorithm Engineering and Experiments [ALENEX 2017]

Reports

• FACTS-IR: Fairness, Accountability, Confidentiality, Transparency, and Safety in Information Retrieval [pdf]
  Alexandra Olteanu, Jean Garcia-Gathright, Maarten de Rijke, Michael D. Ekstrand et al.
  (SIGIR Forum) December 2019, Volume 53 Number 2, pp 20–43
  

Patents

• Wearable Device for Facilitating Interaction between Individuals.
  Preethi Lahoti (Main Inventor), Patrick K. Nicholson, Deepak Ajwani, and Alessandra Sala.
  European Patent Filed 16306640.0. [patent pending]