Email: hao.fang at microsoft dot com

I am a researcher at Microsoft Semantic Machines, working on conversational AI agents and LLM applications.

I received my Ph.D. from Department of Electrical & Computer Engineering at University of Washington, working in the TIAL group with Prof. Mari Ostendorf. Before that, I got my Master degree from Department of Electrical & Computer Engineering, at University of Alberta, Canada, where I worked on compressed sensing with Prof. Sergiy A. Vorobyov and Prof. Hai Jiang. I obtained my Bachelor degree from Beijing University of Posts and Telecommunications, China.

PhD Thesis

Hao Fang. Building A User-Centric and Content-Driven Socialbot. PhD thsis, University of Washington, 2019. [pdf] [slides]

Conference Publications

Kevin Lin, Patrick Xia, and Hao Fang. Few-Shot Adaptation for Parsing Contextual Utterances with LLMs. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings), Nusa Dua, Bali, pp. 348-360, Nov., 2023. [pdf]
Hao Cheng, Hao Fang, Xiaodong Liu, and Jianfeng Gao. Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering. In Proceedings of the 62st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Toronto, Canada, pp. 1864-1875, July, 2023. [pdf]
Hao Fang, Anusha Balakrishnan, Harsh Jhamtani, John Bufe, Jean Crawford, Jayant Krishnamurthy, Adam Pauls, Jason Eisner, Jacob Andreas, and Dan Klein. The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, pp. 5682-5700, July, 2023. [pdf] [codes]
Elias Stengel-Eskin, Emmanouil Antonios Platanios, Adam Pauls, Sam Thomson, Hao Fang, Benjamin Van Durme, Jason Eisner, and Yu Su. When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, pp. 11473-11487, Dec., 2022. [pdf]
Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls, Emmanouil Antonios Platanios, Yu Su, Sam Thomson, and Jacob Andreas. Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, pp. 2810-2823, June, 2021. [pdf]
Hao Cheng, Hao Fang, and Mari Ostendorf. A Dynamic Speaker Model for Conversational Interactions. In Proc. Conf. North American Chapter Assoc. for Computational Linguistics (NAACL), Minneapolis, Minnesota, June 2-7, 2019. [pdf] [codes]
Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A. Smith, and Mari Ostendorf. Sounding Board -- A user-centric and content-driven social chatbot. In Proc. Conf. North American Chapter Assoc. for Computational Linguistics (NAACL) : System Demonstrations, New Orleans, Louisiana, June 1-6, 2018. 1st Prize Winner of 2017 Amazon Alexa Prize. [pdf] [project]
Hao Cheng, Hao Fang, and Mari Ostendorf. A factored neural network model for characterizing online discussions in vector space. In Proc. Conf. Empirical Methods Natural Language Process. (EMNLP), Copenhagen, Denmark, Sept. 7-11, 2017. [pdf] [codes]
Hao Cheng, Hao Fang, Xiaodong He, Jianfeng Gao, and Li Deng. Bi-directional attention with agreement for dependency parsing. In Proc. Conf. Empirical Methods Natural Language Process. (EMNLP), Austin, Texas, Nov. 1-5, 2016. [pdf] [codes]
Hao Fang, Hao Cheng, and Mari Ostendorf. Learning latent local conversation modes for predicting comment endorsement in online discussions. In Proc. Int. Workshop Natural Language Process. for Social Media (SocialNLP), Austin, Texas, Nov. 1, 2016. [pdf]
Hao Fang*, Saurabh Gupta*, Forrest Iandola*, Rupesh K. Srivastava*, Li Deng, Piotr Dollár, Jianfeng Gao, Xiaodong He, Margaret Mitchell, John Platt, C. Lawrence Zitnick, and Geoffrey Zweig. From captions to visual concepts and back. In Proc. Conf. Computer Vision and Pattern Recognition (CVPR), Boston, USA, June 7-12, 2015. 1st prize, tied with Google, at the MS COCO Captioning Challenge 2015. [pdf] [project]
Jacob Devlin, Hao Cheng, Hao Fang, Saurabh Gupta, Li Deng, Xiaodong He, Geoffrey Zweig, and Margaret Mitchell. Language models for image captioning: The quirks and what works. In Proc. Annu. Meeting Assoc. for Computational Linguistics (ACL), Beijing, China, July 26-32, 2015. [pdf]
Aaron Jaech, Vicky Zayats, Hao Fang, Mari Ostendorf, and Hannaneh Hajishirzi. Talking to the crowd: What do people react to in online discussions. In Proc. Conf. Empirical Methods Natural Language Process. (EMNLP), Lisbon, Portugal, Sept. 17-21, 2015. [pdf]
Hao Fang, Sergiy A. Vorobyov, and Hai Jiang. Permutation enhanced parallel reconstruction for compressive sampling. In Proc. Int. Workshop Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Cancun, Mexico, Dec. 13-16, 2015. Finalist of the Best Paper Award. [pdf] [codes]
Hao Cheng, Hao Fang, and Mari Ostendorf. Open-domain name error detection using a multi-task RNN. In Proc. Conf. Empirical Methods Natural Language Process. (EMNLP), Lisbon, Portugal, Sept. 17-21, 2015. [pdf]
Hao Fang, Sergiy A. Vorobyov, Hai Jiang, and Omid Taheri. 2D signal compression via parallel compressed sensing with permutations. In Proc. 46th Annual Asilomar Conf. Signals, Systems, and Computers, Pacific Grove, California, Nov. 4-7, 2012. [pdf] [codes]
Xun Wang, Hao Fang, Xuqi Zhu, Bin Li, and Yu Liu. Sparse filter correlation model based joint reconstruction in distributed compressive video sensing. In Proc. IEEE Int. Conf. on Network Infrastructure and Digital Content, Beijing, China, Sept. 24-26, 2010. [pdf]

Journal Publications

Semantic Machines et al. Task-Oriented Dialogue as Dataflow Synthesis. Transactions of the Association for Computational Linguistics, vol. 8, pp. 556-571, Sept., 2020. [pdf] [codes]
Yanzhang He, Peter Baumann, Hao Fang, Brian Hutchinson, Aaron Jaech, Mari Ostendorf, Eric Fosler-Lussier, and Janet Pierrehumbert. Using pronunciation-based morphological subword units to improve OOV handling in keyword search. IEEE Trans. Audio, Speech, and Language Process., vol. 24, no. 1, pp. 72-92, Jan., 2016. [pdf]
Hao Fang, Sergiy A. Vorobyov, and Hai Jiang. Performance limits of segmented compressive sampling: Correlated measurements versus bits. IEEE Trans. Signal Process., vol. 63, no. 122, pp. 6061-6073, Nov., 2015. [pdf]
Hao Fang, Mari Ostendorf, Peter Baumann, and Janet Pierrehumbert. Exponential language modeling using morphological features and multi-task learning. IEEE Trans. Audio, Speech, and Language Process., vol. 23, no. 12, pp. 2410-2421, Dec., 2015. [pdf]
Hao Fang, Sergiy A. Vorobyov, Hai Jiang, and Omid Taheri. Permutation meets parallel compressed sensing: How to relax restricted isometry property for 2D sparse signals. IEEE Trans. Signal Process., vol. 62, no. 1, pp. 196-210, Jan., 2014. [pdf]

Technical Reports

Boshi Wang, Hao Fang, Jason Eisner, Benjamin Van Durme, and Yu Su. LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error. arXiv:2403.04746 [cs:CL], 2024. [pdf]
Kumar Shridhar, Harsh Jhamtani, Hao Fang, Benjamin Van Durme, Jason Eisner, and Patrick Xia. SCREWS: A Modular Framework for Reasoning with Revisions. arXiv:2309.13075 [cs:AI], 2023. [pdf]
Harsh Jhamtani, Hao Fang, Patrick Xia, Eran Levy, Jacob Andreas, and Ben Van Durme. Natural Language Decomposition and Interpretation of Complex Utterances. arXiv:2305.08677 [cs:CL], 2023. [pdf]
Hao Fang, Hao Cheng, Elizabeth Clark, Ari Holtzman, Maarten Sap, Mari Ostendorf, Yejin Choi, and Noah A. Smith. Sounding Board -- University of Washington’s Alexa Prize Submission”. In Proc. Alexa Prize, 2017. [pdf] [project]
Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, and C. Lawrence Zitnick. Microsoft COCO Captions: Data Collection and Evaluation Server. arXiv:1504.00325 [cs:CV], 2015. [pdf] [codes]