Research

@book{truongkoyejo2026aims,
  title = {AI Measurement Science},
  author = {Truong, Sang T. and Koyejo, Sanmi},
  year = {2026},
  url = {https://aimslab.stanford.edu/textbook/},
  note = {Living textbook},
}

@article{truong2026roadmap,
  title = {A Measurement Science Roadmap: From Human Assessment to AI Evaluation},
  author = {Truong, Sang T. and Goodman, Noah and Brunskill, Emma and Domingue, Ben and Haber, Nick and Koyejo, Sanmi},
  year = {2026},
}

@inproceedings{truong2026scalinglaws,
  title = {Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation},
  author = {Truong, Sang and Tu, Yuheng and Schaeffer, Rylan and Koyejo, Sanmi},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
}

@inproceedings{zhang2026guardrails,
  title = {Why Do Safety Guardrails Degrade Across Languages?},
  author = {Zhang, Max and Patel, Ameen and Truong, Sang T. and Koyejo, Sanmi},
  booktitle = {Conference on Language Modeling},
  year = {2026},
}

@inproceedings{desai2026validity,
  title = {What AI Benchmarks Actually Measure: Adapting Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks},
  author = {Desai, Meera and Truong, Sang T. and Wallach, Hanna and Chouldechova, Alex and Cooper, A. Feder and Garcia-Gathright, Jean and Ho, Daniel E. and Jacobs, Abigail Z. and Koyejo, Sanmi and Pangakis, Nicholas and Wang, Angelina},
  booktitle = {Conference on Language Modeling},
  year = {2026},
}

@inproceedings{hardy2026cartography,
  title = {AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems},
  author = {Hardy, Michael and Reuel, Anka and Zhang, Lijin and Casabianca, Jodi M. and Truong, Sang and Dave, Yash and Lee, Hansol and Domingue, Benjamin and Koyejo, Sanmi},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
}

@inproceedings{corona2026validity,
  title = {Uplifting Human Decision Making in AI Evaluation by Automating Benchmark Validity Analysis},
  author = {Corona, Rodolfo and Truong, Sang and Gupta, Ritwik and Truong, Nhi Ngoc and Tonja, Atnafu Lambebo and Attia, Mena and Faisal, Fahim and Maurya, Kaushal Kumar and Philippy, Fred and Ticona, Belu and Adan, Sumaya Nur and Barez, Fazl and Florez, Omar and Sarin, Supheakmungkol and Srivastava, Aseem and Yi, Xiaoyuan and Haber, Nick and Klein, Dan and Solorio, Thamar and Xie, Xing and Koyejo, Sanmi and Trager, Robert},
  booktitle = {ICML Workshop CTB},
  year = {2026},
}

@article{jiang2026itemlevel,
  title = {AI Evaluation Should Require Standardized Item-Level Data Releases},
  author = {Jiang, Han and Zhang, Susu and Zhu, Dongyao and Bai, Yuzhuo and Truong, Sang T. and Yi, Xiaoyuan and Koyejo, Sanmi and Xie, Xing and Xiao, Ziang},
  year = {2026},
}

@inproceedings{truong2025reeval,
  title = {Reliable and Efficient Amortized Model-based Evaluation},
  author = {Truong, Sang T. and Tu, Yuheng and Liang, Percy and Li, Bo and Koyejo, Sanmi},
  booktitle = {International Conference on Machine Learning},
  year = {2025},
}

@inproceedings{truong2025fantasticbugs,
  title = {Fantastic Bugs and Where to Find Them in AI Benchmarks},
  author = {Truong, Sang T. and Tu, Yuheng and Hardy, Michael and Reuel, Anka and Tang, Zeyu and Burapacheep, Jirayu and Perera, Jonathan and Uwakwe, Chibuike and Domingue, Ben and Haber, Nick and Koyejo, Sanmi},
  booktitle = {Conference on Neural Information Processing Systems},
  year = {2025},
}

@article{kapoor2025prediction,
  title = {Prediction of Item Difficulty for Reading Comprehension Items by Creation of Annotated Item Repository},
  author = {Kapoor, Radhika and Truong, Sang T. and Haber, Nick and Ruiz-Primo, Maria Araceli and Domingue, Benjamin W.},
  journal = {arXiv preprint arXiv:2502.20663},
  year = {2025},
}

@article{truong2026guardians,
  title = {Strategic Evaluation: Incentivizing AI Capability Coverage with Private Benchmarks},
  author = {Truong, Sang and Wang, Serena and Haber, Nick and Koyejo, Sanmi},
  year = {2026},
}

@article{dave2026ecosystem,
  title = {The AI Evaluation Ecosystem},
  author = {Dave, Yash Satish and Truong, Sang T. and Wang, Serena and Koyejo, Sanmi},
  year = {2026},
  note = {*Co-first authors},
}

@article{truong2026predictivecompetition,
  title = {Predictive AI Evaluation Competition},
  author = {Truong, Sang and Salaudeen, Olawale and Truong, Nhi and Wang, Serena and Denisov-Blanch, Yegor and Patel, Fagun and Wang, Angelina and Guerdan, Luke and Xiao, Ziang and Xie, Xing and Haber, Nick and Koyejo, Sanmi},
  year = {2026},
}

@inproceedings{tang2026insitu,
  title = {In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores},
  author = {Tang, Zeyu and Truong, Sang T. and Owens, Deonna and Sharma, Shreyas and Zhang, Yibo Jacky and Miranda, Brando and Koyejo, Sanmi},
  booktitle = {Conference on Language Modeling},
  year = {2026},
}

@inproceedings{patel2026iterative,
  title = {A Dataset for Modeling Iterative Problem-Solving},
  author = {Patel, Fagun and Truong, Sang T. and Nguyen, Duc Q. and Fukuhara, Kaz and Domingue, Ben and Koyejo, Sanmi and Haber, Nick},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
}

@inproceedings{hua2025researchcodebench,
  title = {ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code},
  author = {Hua, Tianyu and Hua, Harper and Xiang, Violet and Klieger, Benjamin and Truong, Sang T. and Liang, Weixin and Sun, Fan-Yun and Haber, Nick},
  booktitle = {Conference on Neural Information Processing Systems},
  year = {2025},
}

@inproceedings{patel2025syntax,
  title = {The Sound of Syntax: Fine-tuning and Comprehensive Evaluation of Language Models for Speech Pathology},
  author = {Patel, Fagun and Nguyen, Duc Q. and Truong, Sang T. and Vaynshtok, Jody and Koyejo, Sanmi and Haber, Nick},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
}

@article{chang2025redteaming,
  title = {Red Teaming ChatGPT in Medicine to Yield Real-World Insights on Model Behavior},
  author = {Chang, Crystal T. and Farah, Hodan and Gui, Haiwen and Rezaei, Shawheen Justin and Bou-Khalil, Charbel and Park, Ye-Jean and Swaminathan, Akshay and Omiye, Jesutofunmi A. and Kolluri, Akaash and Chaurasia, Akash and Lozano, Alejandro and Heiman, Alice and Jia, Allison Sihan and Kaushal, Amit and Jia, Angela and Iacovelli, Angelica and Yang, Archer and Salles, Arghavan and Singhal, Arpita and Narasimhan, Balasubramanian and Belai, Benjamin and Jacobson, Benjamin H. and Li, Binglan and Poe, Celeste H. and Sanghera, Chandan and Zheng, Chenming and Messer, Conor and Kettud, Damien Varid and Pandya, Deven and Kaur, Dhamanpreet and Hla, Diana and Dindoust, Diba and Moehrle, Dominik and Ross, Duncan and Chou, Ellaine and Lin, Eric and Haredasht, Fateme Nateghi and Cheng, Ge and Gao, Irena and Chang, Jacob and Silberg, Jake and Fries, Jason A. and Xu, Jiapeng and Jamison, Joe and Tamaresis, John S. and Chen, Jonathan H. and Lazaro, Joshua and Banda, Juan M. and Lee, Julie J. and Matthys, Karen Ebert and Steffner, Kirsten R. and Tian, Lu and Pegolotti, Lorene and Srinivasan, Malathi and Manimaran, Manivannan and Schwede, Matthew and Zhang, Melissa and Nguyen, Michael and Fathzadeh, Mozziyar and Zhao, Qian and Bajra, Rika and Khurana, Rohit and Azam, Ruhana and Bartlett, Ryan and Truong, Sang T. and Fleming, Scott L. and Raj, Shriti and Behr, Solveig and Onyeka, Sonia and Muppidi, Srinath and Bandali, Tina and Eulalio, Tiffany Y. and Chen, Wenyuan and Zhou, Xiaoyuan and Ding, Yifan and Cui, Yuhui and Tan, Yue and Liu, Yuqi and Shah, Nigam and Daneshjou, Roxana},
  journal = {npj Digital Medicine},
  volume = {8},
  number = {1},
  pages = {149},
  year = {2025},
}

@inproceedings{truong2024villm,
  title = {Crossing Linguistic Horizons: Fine-tuning and Comprehensive Evaluation of Vietnamese Large Language Models},
  author = {Truong, Sang T. and Nguyen, Duc Q. and Nguyen, Toan and Le, Dong D. and Truong, Nhi N. and Quan, Tho and Koyejo, Sanmi},
  booktitle = {Findings of the Association for Computational Linguistics: NAACL},
  year = {2024},
}

@article{niknazar2024guardrail,
  title = {Building a Domain-Specific Guardrail Model in Production},
  author = {Niknazar, Mohammad and Haley, Paul V. and Ramanan, Latha and Truong, Sang T. and Shrinivasan, Yedendra and Bhowmick, Ayan Kumar and Dey, Prasenjit and Jagmohan, Ashish and Maheshwari, Hema and Ponoth, Shom and Smith, Robert and Vempaty, Aditya and Haber, Nick and Koyejo, Sanmi and Sundararajan, Sharad},
  journal = {arXiv preprint arXiv:2408.01452},
  year = {2024},
}

@inproceedings{wang2023decodingtrust,
  title = {DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models},
  author = {Wang, Boxin and Chen, Weixin and Pei, Hengzhi and Xie, Chulin and Kang, Mintong and Zhang, Chenhui and Xu, Chejian and Xiong, Zidi and Dutta, Ritik and Schaeffer, Rylan and Truong, Sang T. and Arora, Simran and Mazeika, Mantas and Hendrycks, Dan and Lin, Zinan and Cheng, Yu and Koyejo, Sanmi and Song, Dawn and Li, Bo},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {36},
  year = {2023},
}

@inproceedings{dang2025preferential,
  title = {Preferential Multi-Objective Bayesian Optimization for Drug Discovery},
  author = {Dang, Tai and Pham, Long-Hung and Truong, Sang T. and Glenn, Ari and Nguyen, Wendy and Pham, Edward A. and Glenn, Jeffrey S. and Koyejo, Sanmi and Luong, Thang},
  booktitle = {ICLR 2025 Workshop on Human-AI Coevolution},
  year = {2025},
}

@inproceedings{griffiths2024gauche,
  title = {GAUCHE: A Library for Gaussian Processes in Chemistry},
  author = {Griffiths, Ryan-Rhys and Klarner, Leo and Moss, Henry and Ravuri, Aditya and Truong, Sang T. and Du, Yuanqi and Stanton, Samuel and Tom, Gary and Rankovic, Bojana and Jamasb, Arian and Deshwal, Aryan and Schwartz, Julius and Tripp, Austin and Kell, Gregory and Frieder, Simon and Bourached, Anthony and Chan, Alex and Moss, Jacob and Guo, Chengzhi and D{\"u}rholt, Johannes Peter and Chaurasia, Saudamini and Park, Ji Won and Strieth-Kalthoff, Felix and Lee, Alpha and Cheng, Bingqing and Aspuru-Guzik, Alan and Schwaller, Philippe and Tang, Jian},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {36},
  year = {2024},
}

@article{schaeffer2024bridging,
  title = {Bridging Associative Memory and Probabilistic Modeling},
  author = {Schaeffer, Rylan and Zahedi, Nika and Khona, Mikail and Pai, Dhruv and Truong, Sang T. and Du, Yilun and Ostrow, Mitchell and Chandra, Sarthak and Carranza, Andres and Fiete, Ila Rani and Gromov, Andrey and Koyejo, Sanmi},
  journal = {arXiv preprint arXiv:2402.10202},
  year = {2024},
}

@article{truong2023teaching,
  title = {Teaching Income Inequality with Data-Driven Visualization},
  author = {Truong, Sang T. and Barreto, Humberto},
  journal = {The American Economist},
  volume = {68},
  number = {1},
  pages = {140--155},
  year = {2023},
}

@article{vogele2022pensa,
  title = {Systematic Analysis of Biomolecular Conformational Ensembles with PENSA},
  author = {V{\"o}gele, Martin and Thomson, Neil J. and Truong, Sang T. and McAvity, Jasper and Zachariae, Ulrich and Dror, Ron O.},
  journal = {The Journal of Chemical Physics},
  year = {2022},
}

@article{duong2022quantum,
  title = {Quantum Neural Architecture Search with Quantum Circuits Metric and Bayesian Optimization},
  author = {Duong, Trong and Truong, Sang T. and Tam, Minh and Bach, Bao and Ryu, Ju Young and Rhee, June-Koo Kevin},
  journal = {arXiv preprint arXiv:2206.14115},
  year = {2022},
}

@article{pham2022agzno,
  title = {Ag/ZnO Heterojunction Decorated on Polypropylene as a Membrane for Photocatalytic Nitrogen Oxide Removal},
  author = {Pham, Van Viet and La, Hai Phong Phan and Le, Hoang Viet and Truong, Sang T. and Nguyen, Thanh Quang and Cao, Thi Mong},
  journal = {Industrial \& Engineering Chemistry Research},
  volume = {61},
  number = {34},
  pages = {12427--12433},
  year = {2022},
}

@article{viet2019sidoped,
  title = {One-pot Hydrothermal Synthesis of Si Doped TiO2 Nanotubes from Commercial Material Sources for Visible Light-Driven Photocatalytic Activity},
  author = {Van Viet, Pham and Huy, Tran Hoang and Truong, Sang T. and Nguyet, Hoang Minh and Thi, Cao Minh},
  journal = {Materials Research Express},
  volume = {6},
  number = {5},
  pages = {055006},
  year = {2019},
}

@article{pham2018silver,
  title = {Silver Nanoparticle Loaded TiO2 Nanotubes with High Photocatalytic and Antibacterial Activity Synthesized by Photoreduction Method},
  author = {Pham, Van Viet and Phan, Thi Kieu Hanh and Mott, Derrick and Maenosono, Shinya and Truong, Sang T. and Cao, Thi Mong},
  journal = {Journal of Photochemistry and Photobiology A: Chemistry},
  volume = {352},
  pages = {106--112},
  year = {2018},
}

@article{viet2018improved,
  title = {An Improved Green Synthesis Method and Escherichia coli Antibacterial Activity of Silver Nanoparticles},
  author = {Van Viet, Pham and Truong, Sang T. and Bich, Nguyen Hoang Ngoc and Thi, Cao Minh},
  journal = {Journal of Photochemistry and Photobiology B: Biology},
  volume = {182},
  pages = {108--114},
  year = {2018},
}

@article{viet2018synthesis,
  title = {Synthesis of a Silver/TiO2 Nanotube Nanocomposite by Gamma Irradiation for Enhanced Photocatalytic Activity under Sunlight},
  author = {Van Viet, Pham and Truong, Sang T. and Hien, Nguyen Quoc and Thi, Cao Minh and Van Hieu, Le},
  journal = {Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms},
  year = {2018},
}

@inproceedings{chen2026interactive,
  title = {Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds},
  author = {Chen, Edward and Truong, Sang T. and Dullerud, Natalie and Koyejo, Sanmi and Guestrin, Carlos},
  booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence},
  year = {2026},
  volume = {337},
  pages = {1105--1153},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v337/chen26a.html},
}

@book{truong2025mlhp,
  title = {Machine Learning from Human Preferences},
  author = {Truong, Sang T. and Haupt, Andreas and Koyejo, Sanmi},
  year = {2026},
  note = {Living textbook},
}

@inproceedings{xiang2025justenough,
  title = {Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning},
  author = {Xiang, Violet and Blagden, Chase and Rafailov, Rafael and Lile, Nathan and Truong, Sang T. and Finn, Chelsea and Haber, Nick},
  booktitle = {NeurIPS 2025 ER Workshop},
  year = {2025},
}

@inproceedings{bhatt2024experimental,
  title = {An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models},
  author = {Bhatt, Gantavya and Chen, Yifang and Das, Arnav and Zhang, Jifan and Truong, Sang T. and Mussmann, Stephen and Zhu, Yinglun and Bilmes, Jeff and Du, Simon and Jamieson, Kevin and Ash, Jordan and Nowak, Robert},
  booktitle = {Findings of the Association for Computational Linguistics: ACL},
  year = {2024},
}

@inproceedings{truong2023thomas,
  title = {Thomas: Learning to Explore Human Preference via Probabilistic Reward Model},
  author = {Truong, Sang T. and Nguyen, Duc Quang and Quan, Tho and Koyejo, Sanmi},
  booktitle = {ICML 2023 Workshop The Many Facets of Preference-Based Learning},
  year = {2023},
}