Searcharxiv⌕ Search

arXiv subjects

Zheng Ning

Publications and source records attributed to Zheng Ning.

15 recordsLinked to original sources
arXiv2025

ALLOY: Generating Reusable Agent Workflows from User Demonstration

Large language models (LLMs) enable end-users to delegate complex tasks to autonomous agents through natural language. However, prompt-based interaction faces critical limitations: Users often struggle to specify procedural requirements for tasks, especially those that don't have a factually correct solution but instead rely on personal preferences, such as posting social media content or planning a trip. Additionally, a ''successful'' prompt for one task may not be reusable or generalizable across similar tasks. We present ALLOY, a system inspired by classical HCI theories on Programming by Demonstration (PBD), but extended to enhance adaptability in creating LLM-based web agents. ALLOY enables users to express procedural preferences through natural demonstrations rather than prompts, while making these procedures transparent and editable through visualized workflows that can be generalized across task variations. In a study with 12 participants, ALLOY's demonstration--based approach outperformed prompt-based agents and manual workflows in capturing user intent and procedural preferences in complex web tasks. Insights from the study also show how demonstration--based interaction complements the traditional prompt-based approach.

cs.HC↗
arXiv2025

AROMA: Mixed-Initiative AI Assistance for Non-Visual Cooking by Grounding Multi-modal Information Between Reality and Videos

Videos offer rich audiovisual information that can support people in performing activities of daily living (ADLs), but they remain largely inaccessible to blind or low-vision (BLV) individuals. In cooking, BLV people often rely on non-visual cues, such as touch, taste, and smell, to navigate their environment, making it difficult to follow the predominantly audiovisual instructions found in video recipes. To address this problem, we introduce AROMA, an AI system that provides timely responses to the user based on real-time, context-aware assistance by integrating non-visual cues perceived by the user, a wearable camera feed, and video recipe content. AROMA uses a mixed-initiative approach: it responds to user requests while also proactively monitoring the video stream to offer timely alerts and guidance. This collaborative design leverages the complementary strengths of the user and AI system to align the physical environment with the video recipe, helping the user interpret their current cooking state and make sense of the steps. We evaluated AROMA through a study with eight BLV participants and offered insights for designing interactive AI systems to support BLV individuals in performing ADLs.

cs.HC↗
arXiv2025

LACE: Exploring Turn-Taking and Parallel Interaction Modes in Human-AI Co-Creation for Iterative Image Generation

This paper introduces LACE, a co-creative system enabling professional artists to leverage generative AI through controlled prompting and iterative refinement within Photoshop. Addressing challenges in precision, iterative coherence, and workflow compatibility, LACE allows flexible control via layer-based editing and dual-mode collaboration (turn-taking and parallel). A pilot study (N=21) demonstrates significant improvements in user satisfaction, ownership, usability, and artistic perception compared to standard AI workflows. We offer comprehensive findings, system details, nuanced user feedback, and implications for integrating generative AI in professional art practices.

cs.HC↗
arXiv2024

A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions

The increasing use of large language model (LLM)-powered code generation tools, such as GitHub Copilot, is transforming software engineering practices. This paper investigates how developers validate and repair code generated by Copilot and examines the impact of code provenance awareness during these processes. We conducted a lab study with 28 participants, who were tasked with validating and repairing Copilot-generated code in three software projects. Participants were randomly divided into two groups: one informed about the provenance of LLM-generated code and the other not. We collected data on IDE interactions, eye-tracking, cognitive workload assessments, and conducted semi-structured interviews. Our results indicate that, without explicit information, developers often fail to identify the LLM origin of the code. Developers generally employ similar validation and repair strategies for LLM-generated code, but exhibit behaviors such as frequent switching between code and comments, different attentional focus, and a tendency to delete and rewrite code. Being aware of the code's provenance led to improved performance, increased search efforts, more frequent Copilot usage, and higher cognitive workload. These findings enhance our understanding of how developers interact with LLM-generated code and carry implications for designing tools that facilitate effective human-LLM collaboration in software development.

cs.SE↗
arXiv2024

PodReels: Human-AI Co-Creation of Video Podcast Teasers

Video podcast teasers are short videos that can be shared on social media platforms to capture interest in the full episodes of a video podcast. These teasers enable long-form podcasters to reach new audiences and gain new followers. However, creating a compelling teaser from an hour-long episode is challenging. Selecting interesting clips requires significant mental effort; editing the chosen clips into a cohesive, well-produced teaser is time-consuming. To support the creation of video podcast teasers, we first investigate what makes a good teaser. We combine insights from both audience comments and creator interviews to determine a set of essential ingredients. We also identify a common workflow shared by creators during the process. Based on these findings, we introduce a human-AI co-creative tool called PodReels to assist video podcasters in creating teasers. Our user study shows that PodReels significantly reduces creators' mental demand and improves their efficiency in producing video podcast teasers.

cs.HC↗
arXiv2024

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

Spatial audio offers more 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.

cs.HC↗
arXiv2024

SPICA: Interactive Video Content Exploration through Augmented Audio Descriptions for Blind or Low-Vision Viewers

Blind or Low-Vision (BLV) users often rely on audio descriptions (AD) to access video content. However, conventional static ADs can leave out detailed information in videos, impose a high mental load, neglect the diverse needs and preferences of BLV users, and lack immersion. To tackle these challenges, we introduce SPICA, an AI-powered system that enables BLV users to interactively explore video content. Informed by prior empirical studies on BLV video consumption, SPICA offers novel interactive mechanisms for supporting temporal navigation of frame captions and spatial exploration of objects within key frames. Leveraging an audio-visual machine learning pipeline, SPICA augments existing ADs by adding interactivity, spatial sound effects, and individual object descriptions without requiring additional human annotation. Through a user study with 14 BLV participants, we evaluated the usability and usefulness of SPICA and explored user behaviors, preferences, and mental models when interacting with augmented ADs.

cs.HC↗
arXiv2024

Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategies

Querying structured databases with natural language (NL2SQL) has remained a difficult problem for years. Recently, the advancement of machine learning (ML), natural language processing (NLP), and large language models (LLM) have led to significant 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 effectiveness 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 effectiveness 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.

cs.HC↗
arXiv2024

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

Relational databases play an important role in business, science, and more. However, many users cannot fully unleash the analytical power of relational databases, because 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 incorrect queries. To address these issues, we introduce a new interaction mechanism that allows users to directly edit a step-by-step explanation of a query to fix errors. Our experiments on multiple datasets, as well as a user study with 24 participants, demonstrate that our approach can achieve better performance than multiple SOTA approaches. Our code and datasets are available at https://github.com/magic-YuanTian/STEPS.

cs.DB↗
arXiv2024

Multi-agent Modeling and Optimal Pumping Control of Magnetic Artificial Cilia

Tiny cilia drive the flow of surrounding fluids through asymmetric jumping, which is one of the main ways for biological organisms to control fluid transport at the micro-scale. Due to its huge application prospects in medical and environmental treatment fields, artificial cilia have attracted widespread research interest in recent years. However, how to model and optimize artificial cilia is currently a common challenge faced by scholars. We model a single artificial cilium driven by a magnetic field as a multi-agent system, where each agent is a magnetic bead, and the interactions between beads are influenced by the magnetic field. Our system is driven by controlling the magnetic field input to achieve fluid transport at low Reynolds number. In order to quantify the flow conveying capacity, we introduce the pumping performance and propose an optimal control problem for pumping performance, and then give its numerical solution. The calculation results indicate that our model and optimal control algorithm can significantly improve the pumping performance of a single cilia.

math.OC↗
arXiv2023

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

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.

cs.HC↗
arXiv2023

Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions

Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP. While studied in tasks such as sentiment analysis and reading comprehension, it remains unexplored in open-domain question answering (OpenQA) due to the difficulty of collecting perturbed questions that satisfy factuality requirements. In this work, we collect minimally edited questions as challenging contrast sets to evaluate OpenQA models. Our collection approach combines both human annotation and large language model generation. We find that the widely used dense passage retriever (DPR) performs poorly on our contrast sets, despite fitting the training set well and performing competitively on standard test sets. To address this issue, we introduce a simple and effective query-side contrastive loss with the aid of data augmentation to improve DPR training. Our experiments on the contrast sets demonstrate that DPR's contrast consistency is improved without sacrificing its accuracy on the standard test sets.

cs.CL↗
arXiv2022

On the Relationship Between Counterfactual Explainer and Recommender

Recommender systems employ machine learning models to learn from historical data to predict the preferences of users. Deep neural network (DNN) models such as neural collaborative filtering (NCF) are increasingly popular. However, the tangibility and trustworthiness of the recommendations are questionable due to the complexity and lack of explainability of the models. To enable explainability, recent techniques such as ACCENT and FIA are looking for counterfactual explanations that are specific historical actions of a user, the removal of which leads to a change to the recommendation result. In this work, we present a general framework for both DNN and non-DNN models so that the counterfactual explainers all belong to it with specific choices of components. This framework first estimates the influence of a certain historical action after its removal and then uses search algorithms to find the minimal set of such actions for the counterfactual explanation. With this framework, we are able to investigate the relationship between the explainers and recommenders. We empirically study two recommender models (NCF and Factorization Machine) and two datasets (MovieLens and Yelp). We analyze the relationship between the performance of the recommender and the quality of the explainer. We observe that with standard evaluation metrics, the explainers deliver worse performance when the recommendations are more accurate. This indicates that having good explanations to correct predictions is harder than having them to wrong predictions. The community needs more fine-grained evaluation metrics to measure the quality of counterfactual explanations to recommender systems.

cs.IR↗
arXiv2018

Novel Multi Agent Models for Chemical Self-assembly

The chemical self-assembly has been considered as one of most important scientific problems in the 21th Century; however, since the process of self-assembly is very complex, there is few mathematic theory for it currently. This paper provides a novel multi-agent model for chemical self-assembly, where the interaction between agents adopts the classic Lennard-Jones potential. Under this model, we propose an optimal problem by taking the temperature as the control input, and choosing the internal energy as the optimal object. A numerical solution for our optimal problem is also developed. Simulations show that our control scheme can improve the product of self-assembly. Further more, we give a strict analysis for the self-assembly model without noise, which corresponds to an attraction-repulsion multi-agent system, and prove it converges to a stable configuration eventually.

math.OC↗