The written exam of the DAIS Qual Exam in Spring 2025 will be held on Monday,  March 3, 2025, at 1pm-5pm in room 2406 Siebel Center. 

This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam will be based on the papers listed here, with 1-2 questions related to each section. If a section has two papers, you can usually expect to see one question related to the section in the qual exam, while if a section has three papers, you can usually expect to see two questions related to the section. You only need to answer four of those questions in the exam, so there is no need for you to read every paper. Instead, it would make sense for you to browse through the list and identify up to 4 sections that have papers that you are most familiar with or most comfortable with reading, and then focus on reading/digesting those papers. In general, you will likely find some sections to be closer to your interests or background than others, and you can focus more on reading the papers in those few sections that seem to be closest to your research interests. We will ask all the qual exam participants to submit the four sections that they have chosen and ensure that there will be questions designed based on those selected sections.   

Section 1

Daniel Rothchild, Ashwinee Panda, Enayat Ullah, Nikita Ivkin, Ion Stoica, Vladimir Braverman, Joseph Gonzalez, Raman Arora. FetchSGD: Communication-Efficient Federated Learning with Sketching, ICML, 2020 https://arxiv.org/abs/2007.07682
Z. Song, Y.Wang, Z. Yu, and L. Zhang.  Sketching for first order method: Efficient algorithm for low-bandwidth channel and vulnerability.  ICML, 2023 https://arxiv.org/abs/2210.08371
M. Shrivastava, B. Isik, Q. Li, S. Koyejo, and A. Banerjee, Sketching for Distributed Deep Learning: A Sharper Analysis, NeurIPS, 2024  

Section 2

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. ICLR 2024. https://arxiv.org/abs/2307.07697
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering. NeurIPS 2024. https://arxiv.org/abs/2402.07630
ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models. EMNLP 2024. https://arxiv.org/abs/2410.22360

Section 3

K. Tieu, D. Fu, Y. Zhu, H. Hamann, and J. He. Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed. NeurIPS 2024 https://openreview.net/pdf?id=266nH7kLSV
J. Wu, E.A. Ainsworth, A. Leakey, H. Wang, and J. He. Graph-Structured Gaussian Processes for Transferable Graph Learning. NeurIPS 2023 https://openreview.net/pdf?id=eZbqD9BoXe
Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y. Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, Qingsong Wen. Time-LLM: Time Series Forecasting by Reprogramming Large Language Models https://arxiv.org/pdf/2310.01728

Section 4

Edwards, Carl and Lai, Tuan and Ros, Kevin and Honke, Garrett and Cho, Kyunghyun and Ji, Heng. 2022. Translation between Molecules and Natural Language. Proc. The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP2022). https://blender.cs.illinois.edu/paper/molt5.pdf
Wang, Hongwei and Li, Weijiang and Jin, Xiaomeng and Cho, Kyunghyun and Ji, Heng and Han, Jiawei and Burke, Martin. 2022. Chemical-Reaction-aware Molecule Representation Learning. Proc. The International Conference on Learning Representations (ICLR2022). https://blender.cs.illinois.edu/paper/moleculerepresentation2022.pdf
Jin, Bowen and Liu, Gang and Han, Chi and Jiang, Meng and Ji, Heng and Han, Jiawei. 2024. Large Language Models on Graphs: A Comprehensive Survey. IEEE Transactions on Knowledge and Data Engineering. https://arxiv.org/pdf/2312.02783

Section 5

Text2SQL is Not Enough: Unifying AI and Databases with TAG, https://arxiv.org/abs/2408.14717
DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing, https://arxiv.org/abs/2410.12189
A Declarative System for Optimizing AI Workloads, https://arxiv.org/pdf/2405.14696

Section 6

Bernstein, Philip A., Colin W. Reid, and Sudipto Das. “Hyder-A Transactional Record Manager for Shared Flash.” CIDR. Vol. 11. 2011. https://www.cidrdb.org/cidr2011/Papers/CIDR11_Paper2.pdf 
Li, Zhaoheng, et al. “Kishu: Time-Traveling for Computational Notebooks.” arXiv preprint arXiv:2406.13856 (2024). https://arxiv.org/pdf/2406.13856 
Moritz, Philipp, et al. “Ray: A distributed framework for emerging {AI} applications.” 13th USENIX symposium on operating systems design and implementation (OSDI 18). 2018. https://www.usenix.org/system/files/osdi18-moritz.pdf 

Section 7

Detecting hallucinations in large language models using semantic entropy
From r to Q∗: Your Language Model is Secretly a Q-Function
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Section 8  

Liu et al. Visual Instruction Tuning https://arxiv.org/abs/2304.08485
Lee et al. Modeling Multimodal Social Interactions: New Challenges and Baslines with Densely-Aligned Representations https://arxiv.org/abs/2403.02090
Ryan et al. Gaze-LLE: Gaze Target Estimation Via Large-Scale Learned Encoders https://arxiv.org/abs/2412.09586

Section 9

Jin, Q., Wang, Z., Floudas, C.S. et al. Matching patients to clinical trials with large language models. Nat Commun 15, 9074 (2024). https://doi.org/10.1038/s41467-024-53081-z
Theodorou, Brandon, Benjamin Danek, Venkat Tummala, Shivam Pankaj Kumar, Bradley Malin, and Jimeng Sun. 2024. “FairPlay: Improving Medical Machine Learning Models with Generative Balancing for Equity and Excellence.” To appear NPJ Digital Medicine. https://doi.org/10.21203/rs.3.rs-5252769/v1.
Wang, Hanyin, Chufan Gao, Bolun Liu, Qiping Xu, Guleid Hussein, Mohamad El Labban, Kingsley Iheasirim, Hariprasad Korsapati, Chuck Outcalt, and Jimeng Sun. 2024. “Adapting Open-Source Large Language Models for Cost-Effective, Expert-Level Clinical Note Generation with on-Policy Reinforcement Learning.” arXiv [Cs.CL]. arXiv. http://arxiv.org/abs/2405.00715.

Section 10

Zhining Liu, Ruizhong Qiu, Zhichen Zeng, Yada Zhu, Hendrik F. Hamann, Hanghang Tong: AIM: Attributing, Interpreting, Mitigating Data Unfairness. KDD 2024: 2014-2025. https://dl.acm.org/doi/10.1145/3637528.3671797
Huan He, Owen Queen, Teddy Koker, Consuelo Cuevas, Theodoros Tsiligkaridis, and Marinka Zitnik. 2023. Domain adaptation for time series under feature and label shifts. In International Conference on Machine Learning. PMLR, 12746–12774. https://arxiv.org/abs/2302.03133
Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, Mingsheng Long: iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. arXiv:2310.06625. https://arxiv.org/abs/2310.06625

Section 11

Engelmann, B., Breuer, T., Friese, J.I., Schaer, P., Fuhr, N. (2024). Context-Driven Interactive Query Simulations Based on Generative Large Language Models. In: Goharian, N., et al. Advances in Information Retrieval. ECIR 2024. Lecture Notes in Computer Science, vol 14609. Springer, Cham. https://doi.org/10.1007/978-3-031-56060-6_12. https://arxiv.org/pdf/2312.09631
Xiang Luo, Zhiwen Tang, Jin Wang, and Xuejie Zhang. 2024. DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5414–5424, Torino, Italia. ELRA and ICCL. https://aclanthology.org/2024.lrec-main.481.pdf 
Lu, W., Ma, P., Yu, J. et al. Metro maps for efficient knowledge learning by summarizing massive electronic textbooks. IJDAR 22, 99–111 (2019). https://doi.org/10.1007/s10032-019-00319-y 

Section 12

Learning the Mechanisms of Network Growth (2024) Touwen et al. Scientific Reports 10.1038/s41598-024-61940-4
A mid-level approach to modeling scientific communities (2019) Harnagel, A. Studies in History and Philosophy of Science Part A https://doi.org/10.1016/j.shpsa.2018.12.010

Section 13

Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig, “Active Retrieval Augmented Generation”, EMNLP-2023, https://aclanthology.org/2023.emnlp-main.495.pdf 
Yunyi Zhang, Ruozhen Yang, Xueqiang Xu, Rui Li, Jinfeng Xiao, Jiaming Shen, Jiawei Han, “TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision”, WWW-2025, https://hanj.cs.illinois.edu/pdf/www25_yyzhang.pdf 

Section 14

Shen, S., Zhang, C., Bialkowski, A., Chen, W., and Xu, M. (2024). Camu: Disentangling causal effects in deep model unlearning. In Proceedings of the 2024 SIAM International Conference on Data Mining (SDM), pages 779–787. (https://epubs.siam.org/doi/pdf/10.1137/1.9781611978032.89)
Rohekar, R. Y., Gurwicz, Y., and Nisimov, S. (2024). Causal interpretation of self-attention in pre-trained transformers. Advances in Neural Information Processing Systems, 36. (https://arxiv.org/pdf/2412.07446)

Section 15

You, J., Gomes-Selman, J. M., Ying, R., & Leskovec, J. (2021, May). Identity-aware graph neural networks. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, No. 12, pp. 10737-10745). (https://arxiv.org/abs/2101.10320)
You, J., Du, T., & Leskovec, J. (2022, August). ROLAND: graph learning framework for dynamic graphs. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (pp. 2358-2366). 2022. (https://arxiv.org/abs/2208.07239)