Ziang Xiao

Ziang Xiao, Xingdi Yuan, Q. Vera Liao et al. · microsoft-research

Qualitative analysis of textual contents unpacks rich and valuable information by assigning labels to the data. However, this process is often labor-intensive, particularly when working with large datasets. While recent AI-based tools demonstrate utility, researchers may not have readily available AI resources and expertise, let alone be challenged by the limited generalizability of those task-specific models. In this study, we explored the use of large language models (LLMs) in supporting deductive coding, a major category of qualitative analysis where researchers use pre-determined codebooks to label the data into a fixed set of codes. Instead of training task-specific models, a pre-trained LLM could be used directly for various tasks without fine-tuning through prompt learning. Using a curiosity-driven questions coding task as a case study, we found, by combining GPT-3 with expert-drafted codebooks, our proposed approach achieved fair to substantial agreements with expert-coded results. We lay out challenges and opportunities in using LLMs to support qualitative coding and beyond.

Ziang Xiao, Tiffany Wenting Li, Karrie Karahalios et al. · microsoft-research

Informed consent is a core cornerstone of ethics in human subject research. Through the informed consent process, participants learn about the study procedure, benefits, risks, and more to make an informed decision. However, recent studies showed that current practices might lead to uninformed decisions and expose participants to unknown risks, especially in online studies. Without the researcher's presence and guidance, online participants must read a lengthy form on their own with no answers to their questions. In this paper, we examined the role of an AI-powered chatbot in improving informed consent online. By comparing the chatbot with form-based interaction, we found the chatbot improved consent form reading, promoted participants' feelings of agency, and closed the power gap between the participant and the researcher. Our exploratory analysis further revealed the altered power dynamic might eventually benefit study response quality. We discussed design implications for creating AI-powered chatbots to offer effective informed consent in broader settings.

Q. Vera Liao, Ziang Xiao · microsoft-research

The recent development of generative large language models (LLMs) poses new challenges for model evaluation that the research community and industry have been grappling with. While the versatile capabilities of these models ignite much excitement, they also inevitably make a leap toward homogenization: powering a wide range of applications with a single, often referred to as ``general-purpose'', model. In this position paper, we argue that model evaluation practices must take on a critical task to cope with the challenges and responsibilities brought by this homogenization: providing valid assessments for whether and how much human needs in diverse downstream use cases can be satisfied by the given model (\textit{socio-technical gap}). By drawing on lessons about improving research realism from the social sciences, human-computer interaction (HCI), and the interdisciplinary field of explainable AI (XAI), we urge the community to develop evaluation methods based on real-world contexts and human requirements, and embrace diverse evaluation methods with an acknowledgment of trade-offs between realisms and pragmatic costs to conduct the evaluation. By mapping HCI and current NLG evaluation methods, we identify opportunities for evaluation methods for LLMs to narrow the socio-technical gap and pose open questions.

Yubin Ge, Ziang Xiao, Jana Diesner et al. · microsoft-research

Generating follow-up questions on the fly could significantly improve conversational survey quality and user experiences by enabling a more dynamic and personalized survey structure. In this paper, we proposed a novel task for knowledge-driven follow-up question generation in conversational surveys. We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge in the context of conversational surveys. Along with the dataset, we designed and validated a set of reference-free Gricean-inspired evaluation metrics to systematically evaluate the quality of generated follow-up questions. We then propose a two-staged knowledge-driven model for the task, which generates informative and coherent follow-up questions by using knowledge to steer the generation process. The experiments demonstrate that compared to GPT-based baseline models, our two-staged model generates more informative, coherent, and clear follow-up questions.

Alessandro Sordoni, Xingdi Yuan, Marc-Alexandre Côté et al. · microsoft-research

Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences. Thus, they can be seen as stochastic language layers in a language network, where the learnable parameters are the natural language prompts at each layer. By stacking two such layers and feeding the output of one layer to the next, we obtain a Deep Language Network (DLN). We first show how to effectively perform prompt optimization for a 1-Layer language network (DLN-1). Then, we present an extension that applies to 2-layer DLNs (DLN-2), where two prompts must be learned. The key idea is to consider the output of the first layer as a latent variable, which requires inference, and prompts to be learned as the parameters of the generative distribution. We first test the effectiveness of DLN-1 in multiple reasoning and natural language understanding tasks. Then, we show that DLN-2 can reach higher performance than a single layer, showing promise that we might reach comparable performance to GPT-4, even when each LLM in the network is smaller and less powerful.

Silviu Pitis, Ziang Xiao, Nicolas Le Roux et al.

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct preference feedback is uninterpretable, difficult to provide where multidimensional criteria may apply, and often inconsistent, either because it is based on incomplete instructions or provided by diverse principals. To address these challenges, we consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We decompose reward modeling error according to these two steps, which suggests that supervising context in addition to context-specific preference may be a viable approach to aligning models with diverse human preferences. For this to work, the ability of models to evaluate context-specific preference is critical. To this end, we contribute context-conditioned preference datasets and accompanying experiments that investigate the ability of language models to evaluate context-specific preference. We use our datasets to (1) show that existing preference models benefit from, but fail to fully consider, added context, (2) finetune a context-aware reward model with context-specific performance exceeding that of GPT-4 and Llama 3 70B on tested datasets, and (3) investigate the value of context-aware preference modeling.

Jie Gao, Kaiser Sun, Jen-tse Huang et al.

Autonomous agents such as Claude Code and Codex now operate for hours or even days. Understanding their runtime behavior has become critical for downstream tasks such as diagnosing inefficiencies, fixing bugs, and ensuring better oversight. A primary way to gain this understanding is analyzing the reasoning trajectories and execution traces these agents generate. Yet such data remains in unstructured natural-language form, making it difficult for humans to interpret at scale. We introduce ACT*ONOMY (a combination of Action and Taxonomy), a taxonomy for describing and analyzing agent behavior at runtime. ACT*ONOMY has two components: (1) the taxonomy itself, developed through Grounded Theory and structured as a three-level hierarchy of 10 actions, 46 subactions, and 120 leaf categories; and (2) an open repository that hosts the living taxonomy, provides an automated analysis pipeline that applies it to agent trajectories analysis, and defines an extension protocol for customization and growth. Our experiments show that ACTONOMY can compare behavioral profiles across agents and characterize a single agent's behavior across diverse trajectories, surfacing patterns indicative of failure modes. By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently, enabling better oversight and control.

Veda Duddu, Jash Rajesh Parekh, Andy Mao et al.

AI-driven conversational coaching is increasingly used to support workplace negotiation, yet prior work assumes uniform effectiveness across users. We challenge this assumption by examining how individual differences, particularly personality traits, moderate coaching outcomes. We conducted a between-subjects experiment (N=267) comparing theory-driven AI (Trucey), general-purpose AI (Control-AI), and a traditional negotiation handbook (Control-NoAI). Participants were clustered into three profiles -- resilient, overcontrolled, and undercontrolled -- based on the Big-Five personality traits and ARC typology. Resilient workers achieved broad psychological gains primarily from the handbook, overcontrolled workers showed outcome-specific improvements with theory-driven AI, and undercontrolled workers exhibited minimal effects despite engaging with the frameworks. These patterns suggest personality as a predictor of readiness beyond stage-based tailoring: vulnerable users benefit from targeted rather than comprehensive interventions. The study advances understanding of personality-determined intervention prerequisites and highlights design implications for adaptive AI coaching systems that align support intensity with individual readiness, rather than assuming universal effectiveness.

Chaoran Chen, Zhiping Zhang, Zeya Chen et al.

LLM-powered computer-use agents (CUAs) are shifting users from direct manipulation to supervisory coordination. Existing oversight mechanisms, however, have largely been studied as isolated interface features, making broader oversight strategies difficult to compare. We conceptualize CUA oversight as a structural coordination problem defined by delegation structure and engagement level, and use this lens to compare four oversight strategies in a mixed-methods study with 48 participants in a live web environment. Our results show that oversight strategy more reliably shaped users' exposure to problematic actions than their ability to correct them once visible. Plan-based strategies were associated with lower rates of agent problematic-action occurrence, but not equally strong gains in runtime intervention success once such actions became visible. On subjective measures, no single strategy was uniformly best, and the clearest context-sensitive differences appeared in trust. Qualitative findings further suggest that intervention depended not only on what controls users retained, but on whether risky moments became legible as requiring judgment during execution. These findings suggest that effective CUA oversight is not achieved by maximizing human involvement alone. Instead, it depends on how supervision is structured to surface decision-critical moments and support their recognition in time for meaningful intervention.

Jonathan Ivey, Anjalie Field, Ziang Xiao

Qualitative interviews provide essential insights into human experiences when they elicit high-quality responses. While qualitative and NLP researchers have proposed various measures of interview quality, these measures lack validation that high-scoring responses actually contribute to the study's goals. In this work, we identify, implement, and evaluate 10 proposed measures of interview response quality to determine which are actually predictive of a response's contribution to the study findings. To conduct our analysis, we introduce the Qualitative Interview Corpus, a newly constructed dataset of 343 interview transcripts with 16,940 participant responses from 14 real research projects. We find that direct relevance to a key research question is the strongest predictor of response quality. We additionally find that two measures commonly used to evaluate NLP interview systems, clarity and surprisal-based informativeness, are not predictive of response quality. Our work provides analytic insights and grounded, scalable metrics to inform the design of qualitative studies and the evaluation of automated interview systems.

Nikhil Sharma, Kenton Murray, Ziang Xiao

Although the multilingual capability of LLMs offers new opportunities to overcome the language barrier, do these capabilities translate into real-life scenarios where linguistic divide and knowledge conflicts between multilingual sources are known occurrences? In this paper, we studied LLM's linguistic preference in a cross-language RAG-based information search setting. We found that LLMs displayed systemic bias towards information in the same language as the query language in both document retrieval and answer generation. Furthermore, in scenarios where no information is in the language of the query, LLMs prefer documents in high-resource languages during generation, potentially reinforcing the dominant views. Such bias exists for both factual and opinion-based queries. Our results highlight the linguistic divide within multilingual LLMs in information search systems. The seemingly beneficial multilingual capability of LLMs may backfire on information parity by reinforcing language-specific information cocoons or filter bubbles further marginalizing low-resource views.

Ruoyao Wang, Graham Todd, Eric Yuan et al.

In this work, we investigate the capacity of language models to generate explicit, interpretable, and interactive world models of scientific and common-sense reasoning tasks. We operationalize this as a task of generating text games, expressed as hundreds of lines of Python code. To facilitate this task, we introduce ByteSized32 (Code: github.com/cognitiveailab/BYTESIZED32), a corpus of 32 reasoning-focused text games totaling 20k lines of Python code. We empirically demonstrate that GPT-4 can use these games as templates for single-shot in-context learning, successfully producing runnable games on unseen topics in 28% of cases. When allowed to self-reflect on program errors, game runnability substantially increases to 57%. While evaluating simulation fidelity is labor-intensive, we introduce a suite of automated metrics to assess game fidelity, technical validity, adherence to task specifications, and winnability, showing a high degree of agreement with expert human ratings. We pose this as a challenge task to spur further development at the juncture of world modeling and code generation.

Chaoran Chen, Zhiping Zhang, Bingcan Guo et al.

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs) of relevant apps, often visually, inferring necessary sequences of actions, and then interacting with GUIs by executing the actions such as clicking, typing, and tapping. To complete real-world tasks, such as filling forms or booking services, GUI agents often need to process and act on sensitive user data. However, this autonomy introduces new privacy and security risks. Adversaries can inject malicious content into the GUIs that alters agent behaviors or induces unintended disclosures of private information. These attacks often exploit the discrepancy between visual saliency for agents and human users, or the agent's limited ability to detect violations of contextual integrity in task automation. In this paper, we characterized six types of such attacks, and conducted an experimental study to test these attacks with six state-of-the-art GUI agents, 234 adversarial webpages, and 39 human participants. Our findings suggest that GUI agents are highly vulnerable, particularly to contextually embedded threats. Moreover, human users are also susceptible to many of these attacks, indicating that simple human oversight may not reliably prevent failures. This misalignment highlights the need for privacy-aware agent design. We propose practical defense strategies to inform the development of safer and more reliable GUI agents.

Kevin Pu, Daniel Lazaro, Ian Arawjo et al. · utoronto

AI programming tools enable powerful code generation, and recent prototypes attempt to reduce user effort with proactive AI agents, but their impact on programming workflows remains unexplored. We introduce and evaluate Codellaborator, a design probe LLM agent that initiates programming assistance based on editor activities and task context. We explored three interface variants to assess trade-offs between increasingly salient AI support: prompt-only, proactive agent, and proactive agent with presence and context (Codellaborator). In a within-subject study (N=18), we find that proactive agents increase efficiency compared to prompt-only paradigm, but also incur workflow disruptions. However, presence indicators and interaction context support alleviated disruptions and improved users' awareness of AI processes. We underscore trade-offs of Codellaborator on user control, ownership, and code understanding, emphasizing the need to adapt proactivity to programming processes. Our research contributes to the design exploration and evaluation of proactive AI systems, presenting design implications on AI-integrated programming workflow.

Nikhil Sharma, Q. Vera Liao, Ziang Xiao

Large language models (LLMs) powered conversational search systems have already been used by hundreds of millions of people, and are believed to bring many benefits over conventional search. However, while decades of research and public discourse interrogated the risk of search systems in increasing selective exposure and creating echo chambers -- limiting exposure to diverse opinions and leading to opinion polarization, little is known about such a risk of LLM-powered conversational search. We conduct two experiments to investigate: 1) whether and how LLM-powered conversational search increases selective exposure compared to conventional search; 2) whether and how LLMs with opinion biases that either reinforce or challenge the user's view change the effect. Overall, we found that participants engaged in more biased information querying with LLM-powered conversational search, and an opinionated LLM reinforcing their views exacerbated this bias. These results present critical implications for the development of LLMs and conversational search systems, and the policy governing these technologies.

Chaoran Chen, Zhiping Zhang, Ibrahim Khalilov et al.

The rise of Large Language Models (LLMs) has revolutionized Graphical User Interface (GUI) automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks of GUI agents and examines how they differ from traditional GUI automation and general autonomous agents. Despite these risks, existing evaluations focus primarily on performance, leaving privacy and security assessments largely unexplored. We review current evaluation metrics for both GUI and general LLM agents and outline five key challenges in integrating human evaluators for GUI agent assessments. To address these gaps, we advocate for a human-centered evaluation framework that incorporates risk assessments, enhances user awareness through in-context consent, and embeds privacy and security considerations into GUI agent design and evaluation.

Christopher Zhang Cui, Xingdi Yuan, Ziang Xiao et al. · microsoft-research

Reasoning is an essential skill to enable Large Language Models (LLMs) to interact with the world. As tasks become more complex, they demand increasingly sophisticated and diverse reasoning capabilities for sequential decision-making, requiring structured reasoning over the context history to determine the next best action. We introduce TALES, a diverse collection of synthetic and human-written text-adventure games designed to challenge and evaluate diverse reasoning capabilities. We present results over a range of LLMs, open- and closed-weights, performing a qualitative analysis on the top performing models. Despite an impressive showing on synthetic games, even the top LLM-driven agents fail to achieve 15% on games designed for human enjoyment. Code and visualization of the experiments can be found at https://microsoft.github.io/tale-suite.

Jingyu Tang, Chaoran Chen, Jiawen Li et al.

The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.

Pengda Wang, Huiqi Zou, Hanjie Chen et al.

Although psychometrics researchers have recently explored the use of large language models (LLMs) as proxies for human participants, LLMs often fail to generate heterogeneous data with human-like diversity, which diminishes their value in advancing social science research. To address these challenges, we explored the potential of the theory-informed Personality Structured Interview (PSI) as a tool for simulating human responses in personality research. In this approach, the simulation is grounded in nuanced real-human interview transcripts that target the personality construct of interest. We have provided a growing set of 357 structured interview transcripts from a representative sample, each containing an individual's response to 32 open-ended questions carefully designed to gather theory-based personality evidence. Additionally, grounded in psychometric research, we have summarized an evaluation framework to systematically validate LLM-generated psychometric data. Results from three experiments demonstrate that well-designed structured interviews could improve human-like heterogeneity in LLM-simulated personality data and predict personality-related behavioral outcomes (i.e., organizational citizenship behaviors and counterproductive work behavior). We further discuss the role of theory-informed structured interviews in LLM-based simulation and outline a general framework for designing structured interviews to simulate human-like data for psychometric research.

Veda Duddu, Jash Rajesh Parekh, Andy Mao et al.

Workplace negotiations are undermined by psychological barriers, which can even derail well-prepared tactics. AI offers personalized and always -- available negotiation coaching, yet its effectiveness for negotiation preparedness remains unclear. We built Trucey, a prototype AI coach grounded in Brett's negotiation model. We conducted a between-subjects experiment (N=267), comparing Trucey, ChatGPT, and a traditional negotiation Handbook, followed by in-depth interviews (N=15). While Trucey showed the strongest reductions in fear relative to both comparison conditions, the Handbook outperformed both AIs in usability and psychological empowerment. Interviews revealed that the Handbook's comprehensive, reviewable content was crucial for participants' confidence and preparedness. In contrast, although participants valued AI's rehearsal capability, its guidance often felt verbose and fragmented -- delivered in bits and pieces that required additional effort -- leaving them uncertain or overwhelmed. These findings challenge assumptions of AI superiority and motivate hybrid designs that integrate structured, theory-driven content with targeted rehearsal, clear boundaries, and adaptive scaffolds to address psychological barriers and support negotiation preparedness.

Yu Lu Liu, Su Lin Blodgett, Jackie Chi Kit Cheung et al.

Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices -- e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks' measurements.

Ruoyao Wang, Graham Todd, Ziang Xiao et al.

Virtual environments play a key role in benchmarking advances in complex planning and decision-making tasks but are expensive and complicated to build by hand. Can current language models themselves serve as world simulators, correctly predicting how actions change different world states, thus bypassing the need for extensive manual coding? Our goal is to answer this question in the context of text-based simulators. Our approach is to build and use a new benchmark, called ByteSized32-State-Prediction, containing a dataset of text game state transitions and accompanying game tasks. We use this to directly quantify, for the first time, how well LLMs can serve as text-based world simulators. We test GPT-4 on this dataset and find that, despite its impressive performance, it is still an unreliable world simulator without further innovations. This work thus contributes both new insights into current LLM's capabilities and weaknesses, as well as a novel benchmark to track future progress as new models appear.

Ziang Xiao, Susu Zhang, Vivian Lai et al.

We address a fundamental challenge in Natural Language Generation (NLG) model evaluation -- the design and evaluation of evaluation metrics. Recognizing the limitations of existing automatic metrics and noises from how current human evaluation was conducted, we propose MetricEval, a framework informed by measurement theory, the foundation of educational test design, for conceptualizing and evaluating the reliability and validity of NLG evaluation metrics. The framework formalizes the source of measurement error and offers statistical tools for evaluating evaluation metrics based on empirical data. With our framework, one can quantify the uncertainty of the metrics to better interpret the result. To exemplify the use of our framework in practice, we analyzed a set of evaluation metrics for summarization and identified issues related to conflated validity structure in human-eval and reliability in LLM-based metrics. Through MetricEval, we aim to promote the design, evaluation, and interpretation of valid and reliable metrics to advance robust and effective NLG models.

Ziang Xiao, Michelle X. Zhou, Wenxi Chen et al.

Interview chatbots engage users in a text-based conversation to draw out their views and opinions. It is, however, challenging to build effective interview chatbots that can handle user free-text responses to open-ended questions and deliver engaging user experience. As the first step, we are investigating the feasibility and effectiveness of using publicly available, practical AI technologies to build effective interview chatbots. To demonstrate feasibility, we built a prototype scoped to enable interview chatbots with a subset of active listening skills - the abilities to comprehend a user's input and respond properly. To evaluate the effectiveness of our prototype, we compared the performance of interview chatbots with or without active listening skills on four common interview topics in a live evaluation with 206 users. Our work presents practical design implications for building effective interview chatbots, hybrid chatbot platforms, and empathetic chatbots beyond interview tasks.

Ziang Xiao, Michelle X. Zhou, Q. Vera Liao et al.

The rise of increasingly more powerful chatbots offers a new way to collect information through conversational surveys, where a chatbot asks open-ended questions, interprets a user's free-text responses, and probes answers whenever needed. To investigate the effectiveness and limitations of such a chatbot in conducting surveys, we conducted a field study involving about 600 participants. In this study with mostly open-ended questions, half of the participants took a typical online survey on Qualtrics and the other half interacted with an AI-powered chatbot to complete a conversational survey. Our detailed analysis of over 5200 free-text responses revealed that the chatbot drove a significantly higher level of participant engagement and elicited significantly better quality responses measured by Gricean Maxims in terms of their informativeness, relevance, specificity, and clarity. Based on our results, we discuss design implications for creating AI-powered chatbots to conduct effective surveys and beyond.