Zheng Zhang

(* indicates equal contribution)

1. C&C 2024

   

   MIMOSA: Human-AI Co-Creation of Computational Spatial Audio Effects on Videos

   Zheng Zhang*, Ning Zheng*, Jerrick Ban, Kaiwen Jiang, Ruohong Gan, Yapeng Tian, and Toby Jia-Jun Li

   In Proceedings of the 15th Conference on Creativity and Cognition, May 2024

   Abs PDF

   Spatial audio offers immersive video consumption experiences to viewers; however, creating and editing spatial audio often expensive and requires specialized equipment and skills, posing a high barrier for amateur video creators. We present MIMOSA, a human-AI co-creation tool that enables amateur users to computationally generate and manipulate spatial audio effects. For a video with only monaural or stereo audio, MIMOSA automatically grounds each sound source to the corresponding sounding object in the visual scene and enables users to further validate and fix the errors in the locations of sounding objects. Users can also augment the spatial audio effect by flexibly manipulating the sounding source positions and creatively customizing the audio effect. The design of MIMOSA exemplifies a human-AI collaboration approach that, instead of utilizing state-of art end-to-end black-box ML models, uses a multistep pipeline that aligns its interpretable intermediate results with the user’s workflow. A lab user study with 15 participants demonstrates MIMOSA’s usability, usefulness, expressiveness, and capability in creating immersive spatial audio effects in collaboration with users.

2. TiiS

   

   Insights into Natural Language Database uery Errors: From Atention Misalignment to User Handling Strategies

   Ning Zheng, Yuan Tian, Zheng Zhang, Tianyi Zhang, and Toby Jia-Jun Li

   In ACM Transactions on Interactive Intelligent Systems, May 2024

   Abs PDF

   Querying structured databases with natural language (NL2SQL) has remained a diicult problem for years. Recently, the advancement of machine learning (ML), natural language processing (NLP), and large language models (LLM) have led to signiicant improvements in performance, with the best model achieving ∼85% percent accuracy on the benchmark Spider dataset. However, there is a lack of a systematic understanding of the types, causes, and efectiveness of error-handling mechanisms of errors for erroneous queries nowadays. To bridge the gap, a taxonomy of errors made by four representative NL2SQL models was built in this work, along with an in-depth analysis of the errors. Second, the causes of model errors were explored by analyzing the model-human attention alignment to the natural language query. Last, a within-subjects user study with 26 participants was conducted to investigate the efectiveness of three interactive error-handling mechanisms in NL2SQL. Findings from this paper shed light on the design of model structure and error discovery and repair strategies for natural language data query interfaces in the future.

3. CHI 2024

   

   CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models

   Jie Gao, Yuchen Guo, Gionnieve Lim, Tianqin Zhang, Zheng Zhang, Toby Jia-Jun Li, and Simon Tangi Perrault

   In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, May 2024

   Abs PDF

   The Collaborative Qualitative Analysis (CQA) process can be time-consuming and resource-intensive, requiring multiple discussions among team members to refine codes and ideas before reaching a consensus. To address these challenges, we introduce CollabCoder, a system leveraging Large Language Models (LLMs) to support three CQA stages: independent open coding, iterative discussions, and the development of a final codebook. In the independent open coding phase, CollabCoder provides AI-generated code suggestions on demand, and allows users to record coding decision-making information (e.g. keywords and certainty) as support for the process. During the discussion phase, CollabCoder helps to build mutual understanding and productive discussion by sharing coding decision-making information with the team. It also helps to quickly identify agreements and disagreements through quantitative metrics, in order to build a final consensus. During the code grouping phase, CollabCoder employs a top-down approach for primary code group recommendations, reducing the cognitive burden of generating the final codebook. An evaluation involving 16 users confirmed the usability and effectiveness of CollabCoder and offered empirical insights into the LLMs’ roles in CQA.

4. EMNLP 2023

   

   Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations

   Yuan Tian, Zheng Zhang, Zheng Ning, Toby Jia-Jun Li, Jonathan K. Kummerfeld, and Tianyi Zhang

   In The 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023

   Abs PDF

   Relational databases play an important role in this Big Data era. However, it is challenging for non-experts to fully unleash the analytical power of relational databases, since they are not familiar with database languages such as SQL. Many techniques have been proposed to automatically generate SQL from natural language, but they suffer from two issues: (1) they still make many mistakes, particularly for complex queries, and (2) they do not provide a flexible way for non-expert users to validate and refine the incorrect queries. To address these issues, we introduce a new interaction mechanism that allows users directly edit a step-by-step explanation of an incorrect SQL to fix SQL errors. Experiments on the Spider benchmark show that our approach outperforms three SOTA approaches by at least 31.6% in terms of execution accuracy. A user study with 24 participants further shows that our approach helped users solve significantly more SQL tasks with less time and higher confidence, demonstrating its potential to expand access to databases, particularly for non-experts.

5. UIST 2023

   

   PEANUT: A Human-AI Collaborative Tool for Annotating Audio-Visual Data

   Zheng Zhang, Zheng Ning, Chenliang Xu, Yapeng Tian, and Toby Jia-Jun Li

   In Proceedings of the 2023 ACM Symposium on User Interface Software and Technology, Oct 2023

   Abs PDF

   Audio-visual learning seeks to enhance the computer’s multi-modal perception leveraging the correlation between the auditory and visual modalities. Despite their many useful downstream tasks, such as video retrieval, AR/VR, and accessibility, the performance and adoption of existing audio-visual models have been impeded by the availability of high-quality datasets. Annotating audio-visual datasets is laborious, expensive, and time-consuming. To address this challenge, we designed and developed an efficient audio-visual annotation tool called Peanut. Peanut’s human-AI collaborative pipeline separates the multi-modal task into two single-modal tasks, and utilizes state-of-the-art object detection and sound-tagging models to reduce the annotators’ effort to process each frame and the number of manually-annotated frames needed. A within-subject user study with 20 participants found that Peanut can significantly accelerate the audio-visual data annotation process while maintaining high annotation accuracy.

6. UIST 2023

   

   VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping

   Zheng Zhang, Jie Gao, Ranjodh Singh Dhaliwal, and Toby Jia-Jun Li

   In Proceedings of the 2023 ACM Symposium on User Interface Software and Technology, Oct 2023

   Abs PDF

   In argumentative writing, writers must brainstorm hierarchical writing goals, ensure the persuasiveness of their arguments, and revise and organize their plans through drafting. Recent advances in large language models (LLMs) have made interactive text generation through a chat interface (e.g., ChatGPT) possible. However, this approach often neglects implicit writing context and user intent, lacks support for user control and autonomy, and provides limited assistance for sensemaking and revising writing plans. To address these challenges, we introduce VISAR, an AI-enabled writing assistant system designed to help writers brainstorm and revise hierarchical goals within their writing context, organize argument structures through synchronized text editing and visual programming, and enhance persuasiveness with argumentation spark recommendations. VISAR allows users to explore, experiment with, and validate their writing plans using automatic draft prototyping. A controlled lab study confirmed the usability and effectiveness of VISAR in facilitating the argumentative writing planning process.

7. CHI 2023

   

   PaTAT: Human-AI Collaborative Qualitative Coding with Explainable Interactive Rule Synthesis

   Zheng Zhang*, Simret Araya Gebreegziabher*, Xiaohang Tang, Yihao Meng, Elena Glassman, and Toby Jia-jun Li

   In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, Apr 2023

   Abs PDF

   The use of AI assistance in data annotation has made significant progress. However, qualitative coding in thematic analysis, as a specific type of annotation task, has unique characteristics that make effective human-AI collaboration difficult. Informed by a formative study, we designed PaTAT, a new AI-enabled tool that uses an interactive program synthesis approach to learn flexible and expressive patterns of user-annotated codes in real-time as users annotate the data. To accommodate the ambiguous, uncertain, and iterative nature of thematic analysis, the use of user-interpretable patterns allows users to understand and validate what the system has learned, make direct fixes, and easily revise, split, or merge previously annotated codes. This new approach also helps human users to learn data characteristics and form new theories in addition to facilitating the “learning” of the AI model. PaTAT’s usefulness and effectiveness were evaluated in a lab user study.

8. IUI 2023

   

   An Empirical Study of Model Errors and User Error Discovery and Repair Strategies in Natural Language Database Queries

   Zheng Zhang*, Zheng Ning*, Tianyi Sun, Yuan Tian, Tianyi Zhang, and Toby Jia-jun Li

   In Proceedings of the 28th International Conference on Intelligent User Interfaces, Mar 2023

   Abs PDF

   Recent advances in machine learning (ML) and natural language processing (NLP) have led to significant improvement in natural language interfaces for structured databases (NL2SQL). Despite the great strides, the overall accuracy of NL2SQL models is still far from being perfect (∼75% on the Spider benchmark). In practice, this requires users to discern incorrect SQL queries generated by a model and manually fix them when using NL2SQL models. Currently, there is a lack of comprehensive understanding about the common errors in auto-generated SQLs and the effective strategies to recognize and fix such errors. To bridge the gap, we (1) performed an in-depth analysis of errors made by three state-of-the-art NL2SQL models; (2) distilled a taxonomy of NL2SQL model errors; and (3) conducted a within-subjects user study with 26 participants to investigate the effectiveness of three representative interactive mechanisms for error discovery and repair in NL2SQL. Findings from this paper shed light on the design of future error discovery and repair strategies for natural language interfaces for structured databases.

9. ACL 2022

   

   Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension

   Ying Xu, Dakuo Wang, Mo Yu, Daniel Ritchie, Bingsheng Yao, Tongshuang Wu, Zheng Zhang, Toby Li, Nora Bradford, Branda Sun, Tran Hoang, Yisi Sang, Yufang Hou, Xiaojuan Ma, Diyi Yang, Nanyun Peng, Zhou Yu, and Mark Warschauer

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), May 2022

   Abs PDF

   Question answering (QA) is a fundamental means to facilitate assessment and training of narrative comprehension skills for both machines and young children, yet there is scarcity of high-quality QA datasets carefully designed to serve this purpose. In particular, existing datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements. Drawing on the reading education research, we introduce FairytaleQA, a dataset focusing on narrative comprehension of kindergarten to eighth-grade students. Generated by educational experts based on an evidence-based theoretical framework, FairytaleQA consists of 10,580 explicit and implicit questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations. Our dataset is valuable in two folds: First, we ran existing QA models on our dataset and confirmed that this annotation helps assess models’ fine-grained learning skills. Second, the dataset supports question generation (QG) task in the education domain. Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.

10. ACL 2022

    

    It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books

    Bingsheng Yao, Dakuo Wang, Tongshuang Wu, Zheng Zhang, Toby Li, Mo Yu, and Ying Xu

    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), May 2022

    Abs PDF

    Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student’s comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.

11. CHI 2022

    

    StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement

    Zheng Zhang, Ying Xu, Yanhao Wang, Bingsheng Yao, Daniel Ritchie, Tongshuang Wu, Mo Yu, Dakuo Wang, and Toby Jia-Jun Li

    In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, May 2022

    Abs PDF

    Despite its benefits for children’s skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions. While recent advances made AI generation of questions from stories possible, the fully-automated approach excludes parent involvement, disregards educational goals, and underoptimizes for child engagement. Informed by need-finding interviews and participatory design (PD) results, we developed StoryBuddy, an AI-enabled system for parents to create interactive storytelling experiences. StoryBuddy’s design highlighted the need for accommodating dynamic user needs between the desire for parent involvement and parent-child bonding and the goal of minimizing parent intervention when busy. The PD revealed varied assessment and educational goals of parents, which StoryBuddy addressed by supporting configuring question types and tracking child progress. A user study validated StoryBuddy’s usability and suggested design insights for future parent-AI collaboration systems.

12. CHI 2020

    

    Race, Gender and Beauty: The Effect of Information Provision on Online Hiring Biases

    Zheng Zhang*, Weiwen Leung*, Daviti Jibuti, Jinhao Zhao, Maximilian Klein, Casey Pierce, Lionel Robert, and Haiyi Zhu

    In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, May 2020

    Abs PDF

    We conduct a study of hiring bias on a simulation platform where we ask Amazon MTurk participants to make hiring decisions for a mathematically intensive task. Our findings suggest hiring biases against Black workers and less attractive workers, and preferences towards Asian workers, female workers and more attractive workers. We also show that certain UI designs, including provision of candidates’ information at the individual level and reducing the number of choices, can significantly reduce discrimination. However, provision of candidate’s information at the subgroup level can increase discrimination. The results have practical implications for designing better online freelance marketplaces.

13. CHI 2019

    

    Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders

    Hao-Fei Cheng, Ruotong Wang, Zheng Zhang, Fiona O’Connell, Terrance Gray, F. Maxwell Harper, and Haiyi Zhu

    In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, May 2019

    Abs PDF

    Increasingly, algorithms are used to make important decisions across society. However, these algorithms are usually poorly understood, which can reduce transparency and evoke negative emotions. In this research, we seek to learn design principles for explanation interfaces that communicate how decision-making algorithms work, in order to help organizations explain their decisions to stakeholders, or to support users’ "right to explanation". We conducted an online experiment where 199 participants used different explanation interfaces to understand an algorithm for making university admissions decisions. We measured users’ objective and self-reported understanding of the algorithm. Our results show that both interactive explanations and "white-box" explanations (i.e. that show the inner workings of an algorithm) can improve users’ comprehension. Although the interactive approach is more effective at improving comprehension, it comes with a trade-off of taking more time. Surprisingly, we also find that users’ trust in algorithmic decisions is not affected by the explanation interface or their level of comprehension of the algorithm.