Tommi S. Jaakkola, Ph.D. Thomas Siebel Professor of Electrical Engineering and Computer Science and the Institute for Data, Systems, and Society MIT Computer Science and Artificial Intelligence Laboratory Stata Center, Bldg 32-G470 Cambridge, MA 02139 tommi at csail dot mit dot edu [home]   [papers]   [research]   [courses]   [people]

The list does not include all recent preprints from arXiv or bioRxiv. For a more complete list, see my Google scholar page

NLP papers

• Cai Zhou, Zekai Wang, Menghua Wu, Qianyu Julie Zhu, Flora C. Shi, Chenyu Wang, Ashia C. Wilson, Tommi Jaakkola, and Stephen Bates.
  Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning.
  Conference on Language Modeling (COLM), 2026.
  [link]
• Yujian Liu, Jiabao Ji, Li An, Tommi Jaakkola, Yang Zhang, and Shiyu Chang.
  How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings.
  Conference on Language Modeling (COLM), 2026.
  [link]
• Cai Zhou, Chenxiao Yang, Yi Hu, Chenyu Wang, Chubin Zhang, Muhan Zhang, Lester Mackey, Tommi Jaakkola, Stephen Bates, and Dinghuai Zhang.
  Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner.
  International Conference on Machine Learning (ICML), 2026.
  [link]
• Chenyu Wang, Paria Rashidinejad, DiJia Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Zejiang Shen, Feiyu Chen, Tommi Jaakkola, Yuandong Tian, and Bo Liu.
  SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models.
  The 14th International Conference on Learning Representations (ICLR), 2026.
  [link]
• Cai Zhou, Chenyu Wang, Dinghuai Zhang, Shangyuan Tong, Yifei Wang, Stephen Bates, and Tommi Jaakkola.
  Next Semantic Scale Prediction via Hierarchical Diffusion Language Models.
  Neural Information Processing Systems (NeurIPS), 2025.
  [link]
• Menghua Wu, Cai Zhou, Stephen Bates, and Tommi Jaakkola.
  Thought calibration: Efficient and confident test-time scaling.
  Empirical Methods in Natural Language Processing (EMNLP), 2025.
  [link]
• Yujian Liu, Shiyu Chang, Tommi Jaakkola, and Yang Zhang.
  Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning.
  The 13th International Conference on Learning Representations (ICLR), 2025.
  [link]
• Victor Quach, Adam Fisch, Tal Schuster, Adam Yala, Jae Ho Sohn, Tommi S. Jaakkola, and Regina Barzilay.
  Conformal Language Modeling.
  The 12th International Conference on Learning Representations (ICLR), 2024.
  [link]
• Bracha Laufer-Goldshtein, Adam Fisch, Regina Barzilay, and Tommi Jaakkola.
  Efficiently Controlling Multiple Risks with Pareto Testing.
  The 11th International Conference on Learning Representations (ICLR), 2023.
  [link]
• Adam Fisch, Tommi Jaakkola, and Regina Barzilay.
  Calibrated Selective Classification.
  Transactions on Machine Learning Research, 2022.
  [link]
• Mo Yu, Yang Zhang, Shiyu Chang, and Tommi S. Jaakkola.
  Understanding Interlocking Dynamics of Cooperative Rationalization.
  Neural Information Processing Systems (NeurIPS), 2021.
  [link]
• Tal Schuster, Adam Fisch, Tommi Jaakkola, and Regina Barzilay.
  Consistent Accelerated Inference via Confident Adaptive Transformers.
  Empirical Methods in Natural Language Processing (EMNLP), 2021.
  [link]
• Adam Fisch, Tal Schuster, Tommi Jaakkola, and Regina Barzilay.
  Few-Shot Conformal Prediction with Auxiliary Tasks.
  International Conference on Machine Learning (ICML), 2021.
  [link]
• Adam Fisch, Tal Schuster, Tommi Jaakkola, and Regina Barzilay.
  Efficient Conformal Prediction via Cascaded Inference with Expanded Admission.
  The Ninth International Conference on Learning Representations (ICLR), 2021.
  [link]
• Tianxiao Shen, Victor Quach, Regina Barzilay, and Tommi Jaakkola.
  Blank Language Models.
  Empirical Methods in Natural Language Processing (EMNLP), 2020.
  [link]
• Shiyu Chang, Yang Zhang, Mo Yu, and Tommi Jaakkola.
  Invariant Rationalization.
  International Conference on Machine Learning (ICML), 2020.
  [link]
• Tianxiao Shen, Jonas Mueller, Regina Barzilay, and Tommi Jaakkola.
  Educating Text Autoencoders: Latent Representation Guidance via Denoising.
  International Conference on Machine Learning (ICML), 2020.
  [link]
• Shiyu Chang, Yang Zhang, Mo Yu, and Tommi Jaakkola.
  A Game Theoretic Approach to Class-wise Selective Rationalization.
  Neural Information Processing Systems (NeurIPS), 2019.
  [pdf]
• Mo Yu, Shiyu Chang, Yang Zhang, and Tommi Jaakkola.
  Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control.
  Empirical Methods in Natural Language Processing (EMNLP), 2019.
  [pdf]
• Karthik Narasimhan, Regina Barzilay, and Tommi Jaakkola.
  Grounding Language for Transfer in Deep Reinforcement Learning.
  Journal of Artificial Intelligence Research, 63, pp. 849-874. 2018.
  [pdf]
• David Alvarez Melis and Tommi S. Jaakkola.
  Gromov-Wasserstein Alignment of Word Embedding Spaces.
  Empirical Methods in Natural Language Processing (EMNLP), 2018.
  [pdf]
• Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola.
  Style Transfer from Non-Parallel Text by Cross-Alignment.
  Advances in Neural Information Processing Systems (NIPS), 2017.
  [link]
• Yuan Zhang, Regina Barzilay, and Tommi Jaakkola.
  Aspect-augmented Adversarial Networks for Domain Adaptation.
  Transactions of the Association for Computational Linguistics (TACL), 2017.
  [pdf]
• David Alvarez Melis and Tommi S. Jaakkola.
  A causal framework for explaining the predictions of black-box sequence-to-sequence models.
  Empirical Methods in Natural Language Processing (EMNLP), 2017.
  [pdf]
• Tao Lei, Regina Barzilay, and Tommi Jaakkola.
  Rationalizing Neural Predictions.
  Empirical Methods in Natural Language Processing (EMNLP), 2016.
  [pdf]
• Youyang Gu, Regina Barzilay, and Tommi S. Jaakkola.
  Food Adulteration Detection using Neural Networks.
  Empirical Methods in Natural Language Processing (EMNLP), 2016.
• Tatsunori B. Hashimoto, David Alvarez Melis, and Tommi S. Jaakkola.
  Word embeddings as metric recovery in semantic spaces.
  Transactions of the Association for Computational Linguistics (TACL), 4. 2016.
  [pdf]
• Yuan Zhang, David Gaddy, Regina Barzilay, and Tommi Jaakkola.
  Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings.
  The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2016.
  [pdf]
• Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Katerina Tymoshenko, Alessandro Moschitti, and Lluis Marquez.
  Semi-supervised Question Retrieval with Gated Convolutions.
  The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2016.
  [pdf]
• Tatsunori B. Hashimoto, David Alvarez-Melis, and Tommi S. Jaakkola.
  Word, graph and manifold embedding from Markov processes.
  arXiv:1509.05808, 2015.
  [link]
• Tao Lei, Regina Barzilay, and Tommi Jaakkola.
  Molding CNNs for Text: Non-linear, Non-consecutive Convolutions.
  Empirical Methods in Natural Language Processing (EMNLP), 2015.
  [pdf] [link]
• Karthik Narasimhan, Regina Barzilay, and Tommi Jaakkola.
  An Unsupervised Method for Uncovering Morphological Chains.
  Transactions of the Association for Computational Linguistics, 3, pp. 157–167. 2015.
  [pdf] [link]
• Yuan Zhang, Tao Lei, Regina Barzilay, and Tommi Jaakkola.
  Greed is Good if Randomized: New Inference for Dependency Parsing.
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014.
  [pdf]
• Tao Lei, Yu Xin, Yuan Zhang, Regina Barzilay, and Tommi Jaakkola.
  Low-Rank Tensors for Scoring Dependency Structures.
  Association for Computational Linguistics (ACL), 2014.
  [pdf]
• Yuan Zhang, Tao Lei, Regina Barzilay, Tommi Jaakkola, and Amir Globerson.
  Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees.
  Association for Computational Linguistics (ACL), 2014.
  [pdf]
• Alexander M. Rush, David Sontag, Michael Collins, and Tommi Jaakkola.
  On Dual Decomposition and Linear Programming Relaxations for Natural Language Processing.
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2010.
  [pdf]
• Terry Koo, Alexander M. Rush, Michael Collins, Tommi Jaakkola, and David Sontag.
  Dual Decomposition for Parsing with Non-Projective Head Automata.
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2010.
  [pdf]