I am a postdoc on the Semantic Scholar team at the Allen Institute for AI (AI2) and in Hanna Hajishirzi’s group at the University of Washington. I work on applied machine learning broadly. Currently, I’m especially interested in information retrieval methods, language model training and text diffusion models. In the past I’ve also worked on text evaluation metrics, hallucination mitigation and steganography.
I received my Ph.D. from the Computer Science Department at Cornell University, where I was advised by Kilian Q Weinberger. During my PhD, I interned at Google with Ni Lao and John Blitzer, at Microsoft Research with Tristan Nauman and at ASAPP with David Sontag.
Before joining Cornell, I completed my undergraduate degree in Math and Computer Science at Harvey Mudd College. There, I conducted research in algorithms for computational biology with Prof. Yi-Chieh (Jessica) Wu.
Outside of research, I enjoy climbing, playing basketball and exploring the outdoors!
Publications and Preprints
Language Models Don’t Know What You Want: Evaluating Personalization in Deep Research Needs Real Users
Nishant Balepur, Malachi Hamada, Varsha Kishore, Sergey Feldman, Amanpreet Singh, and
5 more authors
In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL), 2026.
@inproceedings{balepur2026language,title={Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users},author={Balepur, Nishant and Hamada, Malachi and Kishore, Varsha and Feldman, Sergey and Singh, Amanpreet and Siangliulue, Pao and Chang, Joseph Chee and Choi, Eunsol and Boyd-Graber, Jordan Lee and Naik, Aakanksha},booktitle={Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},acronym={ACL},pages={15910--15944},year={2026},}
Improving attributed long-form question answering with intent awareness
Xinran Zhao, Aakanksha Naik, Jay DeYoung, Joseph Chee Chang, Jena Hwang, and
2 more authors
In International Conference on Learning Representations (ICLR), 2026.
@inproceedings{zhao2026improving,title={Improving attributed long-form question answering with intent awareness},author={Zhao, Xinran and Naik, Aakanksha and DeYoung, Jay and Chang, Joseph Chee and Hwang, Jena and Wu, Sherry and Kishore, Varsha},booktitle={International Conference on Learning Representations},acronym={ICLR},volume={2026},pages={144692--144730},year={2026},}
Astabench: Rigorous benchmarking of ai agents with a scientific research suite
Jonathan Bragg, Mike D’Arcy, Nishant Balepur, Dan Bareket, Bhavana Dalvi Mishra, and
6 more authors
In International Conference on Learning Representations (ICLR), 2026.
@inproceedings{bragg2026astabench,title={Astabench: Rigorous benchmarking of ai agents with a scientific research suite},author={Bragg, Jonathan and D'Arcy, Mike and Balepur, Nishant and Bareket, Dan and Dalvi Mishra, Bhavana and Feldman, Sergey and Haddad, Dany and Hwang, Jena and Jansen, Peter and Kishore, Varsha and others},booktitle={International Conference on Learning Representations},acronym={ICLR},volume={2026},pages={110136--110223},year={2026},}
Dr tulu: Reinforcement learning with evolving rubrics for deep research
Rulin Shao, Akari Asai, Shannon Zejiang Shen, Hamish Ivison, Varsha Kishore, and
6 more authors
In International Conference on Machine Learning (ICML), 2026.
@inproceedings{shao2025dr,title={Dr tulu: Reinforcement learning with evolving rubrics for deep research},author={Shao, Rulin and Asai, Akari and Shen, Shannon Zejiang and Ivison, Hamish and Kishore, Varsha and Zhuo, Jingming and Zhao, Xinran and Park, Molly and Finlayson, Samuel G and Sontag, David and others},booktitle={International Conference on Machine Learning},acronym={ICML},year={2026},}
Synthesizing scientific literature with retrieval-augmented language models
Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, and
6 more authors
@inproceedings{asai2026synthesizing,title={Synthesizing scientific literature with retrieval-augmented language models},author={Asai, Akari and He, Jacqueline and Shao, Rulin and Shi, Weijia and Singh, Amanpreet and Chang, Joseph Chee and Lo, Kyle and Soldaini, Luca and Feldman, Sergey and Kishore, Varsha and others},booktitle={Nature},year={2026},publisher={Nature Publishing Group UK London},}
Reasonir: Training retrievers for reasoning tasks
Rulin Shao, Rui Qiao, Varsha Kishore, Niklas Muennighoff, Xi Victoria Lin, and
6 more authors
@inproceedings{shao2025reasonir,title={Reasonir: Training retrievers for reasoning tasks},author={Shao, Rulin and Qiao, Rui and Kishore, Varsha and Muennighoff, Niklas and Lin, Xi Victoria and Rus, Daniela and Low, Bryan Kian Hsiang and Min, Sewon and Yih, Wen-tau and Koh, Pang Wei and others},booktitle={Conference on Language Modelling},year={2025},}
Diffusion Guided Language Modeling
Justin Lovelace, Varsha Kishore, Yiwei Chen, and Kilian Weinberger
In Findings of the Association for Computational Linguistics ACL 2024 Aug , 2024.
@inproceedings{lovelace-etal-2024-diffusion,title={Diffusion Guided Language Modeling},author={Lovelace, Justin and Kishore, Varsha and Chen, Yiwei and Weinberger, Kilian},booktitle={Findings of the Association for Computational Linguistics ACL 2024},month=aug,year={2024},publisher={Association for Computational Linguistics},url={https://aclanthology.org/2024.findings-acl.887},pages={14936--14952}}
@inproceedings{lovelace2022latent,title={Latent Diffusion for Language Generation},author={Lovelace, Justin and Kishore, Varsha and Wan, Chao and Shaktman, Eliot and Weinberger, Kilian Q},booktitle={Advances in Neural Information Processing Systems},acronym={NeurIPS},year={2023},}
@inproceedings{kishore2023incdsi,title={IncDSI: Incrementally Updatable Document Retrieval},author={Kishore, Varsha and Wan, Chao and Lovelace, Justin and Artzi, Yoav and Weinberger, Kilian Q},booktitle={International Conference on Machine Learning},acronym={ICML},year={2023},}
Correction with Backtracking Reduces Hallucination in Summarization
Zhenzhen Liu, Chao Wan, Varsha Kishore, Jin Zhou, Minmin Chen, and
1 more author
@inproceedings{liu2023correction,title={Correction with Backtracking Reduces Hallucination in Summarization},author={Liu, Zhenzhen and Wan, Chao and Kishore, Varsha and Zhou, Jin and Chen, Minmin and Weinberger, Kilian Q},booktitle={arXiv preprint arXiv:2310.16176},year={2023},}
Learning Iterative Neural Optimizers for Image Steganography
Varsha Kishore, Xiangyu Chen, and Kilian Q Weinberger
In International Conference on Learning Representations Aug (ICLR), 2022.
@inproceedings{chen2023learning,title={Learning Iterative Neural Optimizers for Image Steganography},author={Kishore, Varsha and Chen, Xiangyu and Weinberger, Kilian Q},booktitle={International Conference on Learning Representations},acronym={ICLR},year={2022},}
Harnessing interpretable and unsupervised machine learning to address big data from modern X-ray diffraction
Jordan Venderley, Krishnanand Mallayya, Michael Matty, Matthew Krogstad, Jacob Ruff, and
6 more authors
Proceedings of the National Academy of Sciences Aug , 2022.
@article{venderley2022harnessing,title={Harnessing interpretable and unsupervised machine learning to address big data from modern X-ray diffraction},author={Venderley, Jordan and Mallayya, Krishnanand and Matty, Michael and Krogstad, Matthew and Ruff, Jacob and Pleiss, Geoff and Kishore, Varsha and Mandrus, David and Phelan, Daniel and Poudel, Lekhanath and others},journal={Proceedings of the National Academy of Sciences},volume={119},number={24},pages={e2109665119},year={2022},publisher={National Acad Sciences},}
Fixed Neural Network Steganography: Train the images, not the network
Varsha Kishore, Xiangyu Chen, Yan Wang, Boyi Li, and Kilian Q Weinberger
In International Conference on Learning Representations Aug (ICLR), 2021.
@inproceedings{kishore2021fixed,title={Fixed Neural Network Steganography: Train the images, not the network},author={Kishore, Varsha and Chen, Xiangyu and Wang, Yan and Li, Boyi and Weinberger, Kilian Q},booktitle={International Conference on Learning Representations},acronym={ICLR},year={2021},}
Bertscore: Evaluating text generation with bert
Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi
In International Conference on Learning Representations Aug (ICLR), 2019.
@inproceedings{zhang2019bertscore,title={Bertscore: Evaluating text generation with bert},author={Zhang, Tianyi and Kishore, Varsha and Wu, Felix and Weinberger, Kilian Q and Artzi, Yoav},booktitle={International Conference on Learning Representations},acronym={ICLR},year={2019},}
