Publications

  1. Saparov, A., Pawar, S., Pimpalgaonkar, S., Joshi, N., Pang, R. Y., Padmakumar, V., Kazemi, S. M., Kim, N., & He, H. (2024). Transformers Struggle to Learn to Search. CoRR, abs/2412.04703.
    @article{TransformersSearch2024,
  author = {Saparov, Abulhair and Pawar, Srushti and Pimpalgaonkar, Shreyas and Joshi, Nitish and Pang, Richard Yuanzhe and Padmakumar, Vishakh and Kazemi, Seyed Mehran and Kim, Najoung and He, He},
  title = {Transformers Struggle to Learn to Search},
  journal = {CoRR},
  volume = {abs/2412.04703},
  year = {2024},
  url = {http://arxiv.org/abs/2412.04703},
  eprinttype = {arXiv},
  eprint = {2412.04703},
}
  2. Opedal, A., Shirakami, H., Schölkopf, B., Saparov, A., & Sachan, M. (2024). MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs. CoRR, abs/2410.13502.
    @article{MathGAP2024,
  author = {Opedal, Andreas and Shirakami, Haruki and Sch{\"{o}}lkopf, Bernhard and Saparov, Abulhair and Sachan, Mrinmaya},
  title = {MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs},
  journal = {CoRR},
  volume = {abs/2410.13502},
  year = {2024},
  url = {http://arxiv.org/abs/2410.13502},
  eprinttype = {arXiv},
  eprint = {2410.13502},
}
  3. Rai, D., Zhou, Y., Feng, S., Saparov, A., & Yao, Z. (2024). A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models. CoRR, abs/2407.02646.
    @article{MechInterp2024,
  author = {Rai, Daking and Zhou, Yilun and Feng, Shi and Saparov, Abulhair and Yao, Ziyu},
  title = {A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models},
  journal = {CoRR},
  volume = {abs/2407.02646},
  year = {2024},
  url = {http://arxiv.org/abs/2407.02646},
  eprinttype = {arXiv},
  eprint = {2407.02646},
}
  4. Joshi, N., Saparov, A., Wang, Y., & He, H. (2024). LLMs Are Prone to Fallacies in Causal Inference. To appear in Empirical Methods in Natural Language Processing, EMNLP 2024.
    @article{CausalLLM2024,
  author = {Joshi, Nitish and Saparov, Abulhair and Wang, Yixin and He, He},
  title = {LLMs Are Prone to Fallacies in Causal Inference},
  booktitle = {To appear in Empirical Methods in Natural Language Processing, {EMNLP} 2024},
  year = {2024},
}
  5. Anwar, U., Saparov, A., Rando, J., Paleka, D., Turpin, M., Hase, P., Lubana, E. S., Jenner, E., Casper, S., Sourbut, O., Edelman, B. L., Zhang, Z., Günther, M., Korinek, A., Hernandez-Orallo, J., Hammond, L., Bigelow, E., Pan, A., Langosco, L., Korbak, T., Zhang, H., Zhong, R., hÉigeartaigh, S. Ó., Recchia, G., Corsi, G., Chan, A., Anderljung, M., Edwards, L., Petrov, A., de Witt, C. S., Motwan, S. R., Bengio, Y., Chen, D., Torr, P. H. S., Albanie, S., Maharaj, T., Foerster, J., Tramer, F., He, H., Kasirzadeh, A., Choi, Y., & Krueger, D. (2024). Foundational Challenges in Assuring Alignment and Safety of Large Language Models. Transactions on Machine Learning Research.
    @article{LLMChallenges2024,
  author = {Anwar, Usman and Saparov, Abulhair and Rando, Javier and Paleka, Daniel and Turpin, Miles and Hase, Peter and Lubana, Ekdeep Singh and Jenner, Erik and Casper, Stephen and Sourbut, Oliver and Edelman, Benjamin L. and Zhang, Zhaowei and Günther, Mario and Korinek, Anton and Hernandez-Orallo, Jose and Hammond, Lewis and Bigelow, Eric and Pan, Alexander and Langosco, Lauro and Korbak, Tomasz and Zhang, Heidi and Zhong, Ruiqi and h{\'E}igeartaigh, Se{\'a}n {\'O} and Recchia, Gabriel and Corsi, Giulio and Chan, Alan and Anderljung, Markus and Edwards, Lilian and Petrov, Aleksandar and de Witt, Christian Schroeder and Motwan, Sumeet Ramesh and Bengio, Yoshua and Chen, Danqi and Torr, Philip H.S. and Albanie, Samuel and Maharaj, Tegan and Foerster, Jakob and Tramer, Florian and He, He and Kasirzadeh, Atoosa and Choi, Yejin and Krueger, David},
  title = {Foundational Challenges in Assuring Alignment and Safety of Large Language Models},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2024},
}
  6. Opedal, A., Stolfo, A., Shirakami, H., Jiao, Y., Cotterell, R., Schölkopf, B., Saparov, A., & Sachan, M. (2024). Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? Forty-first International Conference on Machine Learning, ICML 2024.
    @article{MWPBiases2024,
  author = {Opedal, Andreas and Stolfo, Alessandro and Shirakami, Haruki and Jiao, Ying and Cotterell, Ryan and Sch{\"{o}}lkopf, Bernhard and Saparov, Abulhair and Sachan, Mrinmaya},
  title = {Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?},
  booktitle = {Forty-first International Conference on Machine Learning, {ICML} 2024},
  year = {2024},
}
  7. Joshi, N.*, Rando, J.*, Saparov, A., Kim, N., & He, H. (2024). Personas as a Way to Model Truthfulness in Language Models. To appear in Empirical Methods in Natural Language Processing, EMNLP 2024.
    *equal contribution
    @article{Personas2023,
  author = {Joshi, Nitish and Rando, Javier and Saparov, Abulhair and Kim, Najoung and He, He},
  title = {Personas as a Way to Model Truthfulness in Language Models},
  booktitle = {To appear in Empirical Methods in Natural Language Processing, {EMNLP} 2024},
  year = {2024},
}
  8. Saparov, A., Pang, R. Y., Padmakumar, V., Joshi, N., Kazemi, M., Kim, N., & He, H. (2023). Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples. Advances in Neural Information Processing Systems 36, NeurIPS 2023.
    @article{PrOntoQAOOD,
  title = {Testing the General Deductive Reasoning Capacity of Large Language Models Using {OOD} Examples},
  author = {Saparov, Abulhair and Pang, Richard Yuanzhe and Padmakumar, Vishakh and Joshi, Nitish and Kazemi, Mehran and Kim, Najoung and He, He},
  booktitle = {Advances in Neural Information Processing Systems 36, NeurIPS 2023},
  year = {2023},
}
  9. Zheng, H., & Saparov, A. (2023). Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis. Empirical Methods in Natural Language Processing, EMNLP 2023. Association for Computational Linguistics.
    @inproceedings{ZhengSaparov2023,
  author = {Zheng, Hongyi and Saparov, Abulhair},
  title = {Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis},
  booktitle = {Empirical Methods in Natural Language Processing, {EMNLP} 2023},
  publisher = {Association for Computational Linguistics},
  year = {2023},
}
  10. Mavi, V., Saparov, A., & Zhao, C. (2023). Retrieval-Augmented Chain-of-Thought in Semi-structured Domains. Natural Legal Language Processing Workshop @ EMNLP 2023.
    @inproceedings{MaviSaparovZhao2023,
  author = {Mavi, Vaibhav and Saparov, Abulhair and Zhao, Chen},
  title = {Retrieval-Augmented Chain-of-Thought in Semi-structured Domains},
  booktitle = {Natural Legal Language Processing Workshop @ EMNLP 2023},
  year = {2023},
}
  11. Opedal, A., Stoehr, N., Saparov, A., & Sachan, M. (2023). World Models for Math Story Problems. Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics.
    @inproceedings{Opedal2023,
  author = {Opedal, Andreas and Stoehr, Niklas and Saparov, Abulhair and Sachan, Mrinmaya},
  title = {World Models for Math Story Problems},
  booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023},
  series = {Findings of {ACL}},
  publisher = {Association for Computational Linguistics},
  year = {2023},
}
  12. Saparov, A., & He, H. (2023). Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought. International Conference on Learning Representations.
    @inproceedings{SaparovHe2023,
  title = {Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought},
  author = {Saparov, Abulhair and He, He},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
}
  13. Saparov, A. (2022). Towards General Natural Language Understanding with Probabilistic Worldbuilding. PhD thesis, Carnegie Mellon University.
    @phdthesis{SaparovThesis,
  author = {Saparov, Abulhair},
  title = {Towards General Natural Language Understanding with Probabilistic Worldbuilding},
  school = {Carnegie Mellon University},
  year = {2022},
}
  14. Saparov, A., & Mitchell, T. M. (2022). Towards General Natural Language Understanding with Probabilistic Worldbuilding. Transactions of the Association for Computational Linguistics, 10, 325–342.
    @article{SaparovMitchell22,
  author = {Saparov, Abulhair and Mitchell, Tom M.},
  title = {Towards General Natural Language Understanding with Probabilistic Worldbuilding},
  journal = {Transactions of the Association for Computational Linguistics},
  volume = {10},
  pages = {325-342},
  year = {2022},
  month = apr,
  issn = {2307-387X},
  doi = {10.1162/tacl_a_00463},
}
  15. Saparov, A. (2022). A Probabilistic Generative Grammar for Semantic Parsing. CoRR, abs/1606.06361.
    @article{Saparov22,
  author = {Saparov, Abulhair},
  title = {A Probabilistic Generative Grammar for Semantic Parsing},
  journal = {CoRR},
  volume = {abs/1606.06361},
  year = {2022},
  url = {http://arxiv.org/abs/1606.06361},
  eprinttype = {arXiv},
  eprint = {1606.06361},
}
  16. Platanios, E. A.*, Saparov, A.*, & Mitchell, T. M. (2020). Jelly Bean World: A Testbed for Never-Ending Learning. International Conference on Learning Representations.
    *equal contribution
    @inproceedings{PlataniosSaparov2020,
  title = {Jelly Bean World: A Testbed for Never-Ending Learning},
  author = {Platanios, Emmanouil Antonios and Saparov, Abulhair and Mitchell, Tom M.},
  booktitle = {International Conference on Learning Representations},
  year = {2020},
}
  17. Mitchell, T. M., Cohen, W., Hruschka, E., Talukdar, P., Yang, B., Betteridge, J., Carlson, A., Dalvi, B., Gardner, M., Kisiel, B., Krishnamurthy, J., Lao, N., Mazaitis, K., Mohammad, T., Nakashole, N., Platanios, E. A., Ritter, A., Samadi, M., Settles, B., Wang, R., Wijaya, D., Gupta, A., Chen, X., Saparov, A., Greaves, M., & Welling, J. (2018). Never-Ending Learning. Commun. ACM, 61(5), 103–115.
    @article{Mitchell2018,
  author = {Mitchell, Tom M. and Cohen, William and Hruschka, Estevam and Talukdar, Partha and Yang, Bishan and Betteridge, Justin and Carlson, Andrew and Dalvi, Bhavana and Gardner, Matthew and Kisiel, Bryan and Krishnamurthy, Jayant and Lao, Ni and Mazaitis, Kathryn and Mohammad, Thahir and Nakashole, Ndapa and Platanios, Emmanouil A. and Ritter, Alan and Samadi, Mehdi and Settles, Burr and Wang, Richard and Wijaya, Derry and Gupta, Abhinav and Chen, Xinlei and Saparov, Abulhair and Greaves, Malcolm and Welling, Joel},
  title = {Never-Ending Learning},
  year = {2018},
  issue_date = {April 2018},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  volume = {61},
  number = {5},
  issn = {0001-0782},
  doi = {10.1145/3191513},
  journal = {Commun. ACM},
  month = apr,
  pages = {103–115},
}
  18. Saparov, A., Saraswat, V., & Mitchell, T. (2017). A Probabilistic Generative Grammar for Semantic Parsing. Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). Association for Computational Linguistics, 248–259.
    @inproceedings{Saparov2017,
  author = {Saparov, Abulhair and Saraswat, Vijay and Mitchell, Tom},
  title = {A Probabilistic Generative Grammar for Semantic Parsing},
  booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  month = aug,
  year = {2017},
  publisher = {Association for Computational Linguistics},
  pages = {248--259},
}
  19. Saparov, A., & Schwemmer, M. A. (2015). Effects of Passive Dendritic Tree Properties on the Firing Dynamics of A Leaky-Integrate-and-Fire Neuron. Mathematical Biosciences, 269, 61–75.
    @article{Saparov2015,
  title = {Effects of Passive Dendritic Tree Properties on the Firing Dynamics of A Leaky-Integrate-and-Fire Neuron},
  journal = {Mathematical Biosciences},
  volume = {269},
  pages = {61 - 75},
  year = {2015},
  issn = {0025-5564},
  author = {Saparov, Abulhair and Schwemmer, Michael A.}
}
  20. Mitchell, T. M., Cohen, W., Hruschka, E., Talukdar, P., Betteridge, J., Carlson, A., Dalvi, B., Gardner, M., Kisiel, B., Krishnamurthy, J., Lao, N., Mazaitis, K., Mohammad, T., Nakashole, N., Platanios, E. A., Ritter, A., Samadi, M., Settles, B., Wang, R., Wijaya, D., Gupta, A., Chen, X., Saparov, A., Greaves, M., & Welling, J. (2015). Never-Ending Learning. AAAI.
    @inproceedings{Mitchell2015,
  author = {Mitchell, Tom M. and Cohen, William and Hruschka, Estevam and Talukdar, Partha and Betteridge, Justin and Carlson, Andrew and Dalvi, Bhavana and Gardner, Matthew and Kisiel, Bryan and Krishnamurthy, Jayant and Lao, Ni and Mazaitis, Kathryn and Mohammad, Thahir and Nakashole, Ndapa and Platanios, Emmanouil A. and Ritter, Alan and Samadi, Mehdi and Settles, Burr and Wang, Richard and Wijaya, Derry and Gupta, Abhinav and Chen, Xinlei and Saparov, Abulhair and Greaves, Malcolm and Welling, Joel},
  booktitle = {AAAI},
  note = {: Never-Ending Learning in AAAI-2015},
  title = {Never-Ending Learning},
  year = {2015},
}
  21. Chen, X., Saparov, A., Pang, B., & Funkhouser, T. (2012). Schelling Points on 3D Surface Meshes. ACM Transactions on Graphics (Proc. SIGGRAPH).
    @article{Chen2012,
  author = {Chen, Xiaobai and Saparov, Abulhair and Pang, Bill and Funkhouser, Thomas},
  title = {Schelling Points on {3D} Surface Meshes},
  journal = {ACM Transactions on Graphics (Proc. SIGGRAPH)},
  year = {2012},
  month = aug,
}