| 2025 | EMNLP | Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models. | Tomohiro Sawada, Kartik Goyal |
| 2025 | IJCNLP | Cascaded Information Disclosure for Generalized Evaluation of Problem Solving Capabilities. | Yunxiang Yan, Tomohiro Sawada, Kartik Goyal |
| 2024 | ACL | MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy. | Davis Yoshida, Kartik Goyal, Kevin Gimpel |
| 2024 | ICDAR | Clustering Running Titles to Understand the Printing of Early Modern Books. | Nikolai Vogler, Kartik Goyal, Samuel V. Lemley, D. J. Schuldt, Christopher N. Warren, Max G'Sell, Taylor Berg-Kirkpatrick |
| 2023 | AAAI | Contrastive Attention Networks for Attribution of Early Modern Print. | Nikolai Vogler, Kartik Goyal, Kishore PV Reddy, Elizaveta Pertseva, Samuel V. Lemley, Christopher N. Warren, Max G'Sell, Taylor Berg-Kirkpatrick |
| 2022 | ACL | Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models. | Fatemehsadat Mireshghallah, Kartik Goyal, Taylor Berg-Kirkpatrick |
| 2022 | EMNLP | Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. | Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, Reza Shokri |
| 2022 | ICLR | Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings. | Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick |
| 2020 | ACL | A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing. | Kartik Goyal, Chris Dyer, Christopher N. Warren, Max G'Sell, Taylor Berg-Kirkpatrick |
| 2019 | NAACL | An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search. | Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick |
| 2018 | AAAI | A Continuous Relaxation of Beam Search for End-to-End Training of Neural Sequence Models. | Kartik Goyal, Graham Neubig, Chris Dyer, Taylor Berg-Kirkpatrick |
| 2017 | ACL | Differentiable Scheduled Sampling for Credit Assignment. | Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick |
| 2016 | COLING | Named Entity Recognition for Linguistic Rapid Response in Low-Resource Languages: Sorani Kurdish and Tajik. | Patrick Littell, Kartik Goyal, David R. Mortensen, Alexa Little, Chris Dyer, Lori S. Levin |
| 2016 | COLING | PanPhon: A Resource for Mapping IPA Segments to Articulatory Feature Vectors. | David R. Mortensen, Patrick Littell, Akash Bharadwaj, Kartik Goyal, Chris Dyer, Lori S. Levin |
| 2016 | EMNLP | Posterior regularization for Joint Modeling of Multiple Structured Prediction Tasks with Soft Constraints. | Kartik Goyal, Chris Dyer |
| 2016 | LREC | Bridge-Language Capitalization Inference in Western Iranian: Sorani, Kurmanji, Zazaki, and Tajik. | Patrick Littell, David R. Mortensen, Kartik Goyal, Chris Dyer, Lori S. Levin |
| 2014 | COLING | Unsupervised Word Sense Induction using Distributional Statistics. | Kartik Goyal, Eduard H. Hovy |
| 2013 | ACL | A Structured Distributional Semantic Model for Event Co-reference. | Kartik Goyal, Sujay Kumar Jauhar, Huiying Li, Mrinmaya Sachan, Shashank Srivastava, Eduard H. Hovy |
| 2013 | ACL | A Structured Distributional Semantic Model : Integrating Structure with Semantics. | Kartik Goyal, Sujay Kumar Jauhar, Huiying Li, Mrinmaya Sachan, Shashank Srivastava, Eduard H. Hovy |