arXiv subjects

Ujwal Gadiraju

Publications and source records attributed to Ujwal Gadiraju.

At least 19 recordsLinked to original sources

arXiv2026

Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors

Programming error messages are critical for software development, yet they remain difficult for novice programmers to interpret. While Large Language Models (LLMs) can rewrite these errors into clearer explanations, it remains unclear whether increased readability improves objective debugging performance or how explanation styles should align with programmer skill. We present a multi-stage crowdsourced study N=103 evaluating skill-targeted, LLM-generated Python error messages. Using a custom proficiency assessment, we categorized participants by skill level and tested standard interpreter messages against two LLM-generated styles: pragmatic (action-oriented) and contingent (scaffolded explanations). We measured both objective debugging metrics (fix rate, attempts, time-to-fix) and subjective perceptions (readability, cognitive load, tone). Our results show that while LLM-rewritten messages significantly improved subjective evaluations, with pragmatic messages rated as clearer and less cognitively demanding, these perceived gains did not translate into statistically significant improvements in objective debugging performance. This highlights a critical human-AI complementarity gap: explanations that feel better to users do not necessarily make them more effective debuggers. We discuss design implications for adaptive AI feedback systems, arguing that future tools should pivot from static skill-targeted rewriting toward dynamic adjustments based on a user's real-time repair trajectory.

cs.SE↗

arXiv2026

The Belief Update Gate: Separating Inertia from Learning in Human-AI Interaction

Repeated human-AI interaction is often analyzed through pooled belief-updating slopes: users observe AI successes and failures, revise reported beliefs in the feedback-consistent direction, but appear conservative on average. We show that such averages can obscure an important distinction between whether an elicited belief report changes at all and how it changes conditional on movement. We refer to this measurement-aware decomposition as the belief update gate. Reanalyzing a multi-task human-AI decision-making dataset with 240 participants, 7,200 trials, and three task domains, we find substantial non-movement in reported beliefs: 67.3% of trial-level belief changes are exactly zero, and 76.4% are smaller than five percentage points. Separating non-moving from moving reports changes the descriptive interpretation of pooled conservatism: the within-trajectory slope rises from 0.494 overall to 0.949 among rows with nonzero movement. Since this latter estimate conditions on observed movement, we interpret it as a descriptive decomposition rather than as evidence of a near-Bayesian latent learning process. Complementary hurdle style analyses (i.e., modeling zero vs. non-zero changes before predicting update magnitude) show that the absolute discrepancy between feedback and entering belief predicts whether a report changes, while the signed feedback discrepancy predicts the direction and magnitude of change among reports that move. Importantly, observed non-movement does not distinguish genuine latent belief inertia from small unexpressed updates, rounding, or other reporting processes. These findings show that calibration analyses of repeated human--AI interaction should distinguish visible non-movement in elicited belief reports from updating conditional on movement rather than treating reported beliefs as a single continuous updating process.

cs.HC↗

arXiv2026

RecQuest: Towards Estimating User Domain Knowledge in Conversational Recommender Systems

The ideal conversational recommender system (CRS) acts like a savvy salesperson, adapting its language and suggestions to a user's expertise level. However, most current systems treat all users as experts, leading to frustrating and inefficient interactions when users are unfamiliar with a domain. Systems that can adapt their conversational strategies to a user's knowledge level stand to offer a much more natural and effective experience. To enable such adaptation, a CRS must first be able to estimate a user's domain knowledge from interaction signals. Yet, accurately estimating knowledge typically requires tailored interactions to elicit those signals in the first place, creating a fundamental chicken-and-egg problem. In this work, we take a first step toward breaking this dependency by introducing a new task: estimating user domain knowledge directly from conversational transcripts. A key obstacle to such estimation is the lack of suitable data; to our knowledge, no existing dataset captures the conversational behaviors of users with varying levels of domain knowledge. Furthermore, in most dialogue collection protocols, users are free to express their own preferences, which tends to concentrate on popular items and well-known features, offering little insight into how novices explore or learn about unfamiliar features. To address this, we design RecQuest, a game-with-a-purpose data collection protocol that elicits varied expressions of knowledge while using a target-aware CRS to guide interactions, release the resulting dataset, and provide baseline methods and analyses to support future work on user-knowledge-aware CRS.

cs.IR↗

arXiv2026

AI at the Front Lines of Platform Governance: Using LLMs to Support Illegal Content Reporting under the Digital Services Act

Illegal content reporting mechanisms are a key technical and organizational measure through which online platforms address illegal content under the European Union Digital Services Act (DSA). Article 16 requires user notices to be sufficiently substantiated and submitted in good faith, placing users in the difficult position of interpreting legal and procedural language and translating ambiguous content into legally meaningful categories and reasons. We investigate how large language model (LLM)-based assistants can support this reporting process. In a controlled user study (N = 450) using an interface modeled on a major platform reporting workflow, we compare three conditions: unaided reporting, a conventional explainable AI assistant (XAI) that suggests a single legal category with a rationale, and an evaluative AI assistant (EvalAI) that presents balanced pro and con arguments across candidate legal provisions. We further examine these assistance forms under systematically varied AI error regimes. Our results show that EvalAI improves provision-level accuracy under AI error and reduces misclassification distance relative to conventional XAI, particularly for near-miss and overbreadth errors. When AI output is correct, conventional XAI enables faster decisions, but neither AI assistance form reliably improves the quality of users' substantiated explanations relative to unaided reporting. We discuss design implications for compliance-oriented reporting interfaces, highlighting trade-offs between accuracy, deliberation, explanation quality, and vulnerability to misleading AI output.

cs.HC↗

arXiv2026

"Label from Somewhere": Reflexive Annotating for Situated AI Alignment

AI alignment relies on annotator judgments, yet annotation pipelines often treat annotators as interchangeable, obscuring how their social position shapes annotation. We introduce reflexive annotating as a probe that invites crowd workers to reflect on how their positionality informs subjective annotation judgments in a language model alignment context. Through a qualitative study with crowd workers (N=30) and follow-up interviews (N=5), we examine how our probe shapes annotators' behaviour, experience, and the situated metadata it elicits. We find that reflexive annotating captures epistemic metadata beyond static demographics by eliciting intersectional reasoning, surfacing positional humility, and nudging viewpoint change. Crucially, we also denote tensions between reflexive engagement and affective demands such as emotional exposure. We discuss the implications of our work for richer value elicitation and alignment practices that treat annotator judgments as situated and selectively integrate positional metadata.

cs.HC↗

arXiv2026

Keeping an Eye on AI: A Framework for Effective Human Oversight of AI Systems

The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a common foundational understanding: oversight architectures are not well defined, the roles involved remain unclear, and implementation steps are opaque. Hence, researchers and practitioners struggle to determine how to design, implement, and evaluate systems that enable effective human oversight. This paper advances a practical framework for effective human oversight of AI systems, based on a cross-disciplinary perspective that draws on insights from computer science, human-computer interaction, psychology, philosophy, and law. The core contributions are: (1) a foundational framework, with a working definition, architecture and processes for effective human oversight of AI systems; (2) an initial template for documenting oversight architectures and processes, applied to diverse domains; and (3) a synthesis of open research challenges that need to be considered in the emerging field of effective human oversight of AI systems.

cs.CY↗

arXiv2026

The Data-Dollars Tradeoff: Privacy Harms vs. Economic Risk in Personalized AI Adoption

Privacy concerns significantly impact AI adoption, yet little is known about how information environments shape user responses to data leak threats. We conducted a 2 x 3 between-subjects experiment (N=610) examining how risk versus ambiguity about privacy leaks affects the adoption of AI personalization. Participants chose between standard and AI-personalized product baskets, with personalization requiring data sharing that could leak to pricing algorithms. Under risk (30% leak probability), we found no difference in AI adoption between privacy-threatening and neutral conditions (ca. 50% adoption). Under ambiguity (10-50% range), privacy threats significantly reduced adoption compared to neutral conditions. This effect holds for sensitive demographic data as well as anonymized preference data. Users systematically over-bid for privacy disclosure labels, suggesting strong demand for transparency institutions. Notably, privacy leak threats did not affect subsequent bargaining behavior with algorithms. Our findings indicate that ambiguity over data leaks, rather than only privacy preferences per se, drives avoidance behavior among users towards personalized AI.

cs.HC↗

arXiv2026

Belief Updating and Delegation in Multi-Task Human-AI Interaction: Evidence from Controlled Simulations

Large language models (LLMs) increasingly support heterogeneous tasks within a single interface, requiring users to form, update, and act upon beliefs about one system across domains with different reliability profiles. Understanding how such beliefs transfer across tasks and shape delegation is therefore critical for the design of multipurpose AI systems. We report a preregistered experiment (N=240; 7,200 trials) in which participants interacted with a controlled AI simulation across grammar checking, travel planning, and visual question answering, each with fixed, domain-typical accuracy levels. Delegation was operationalized as a binary reliance decision: accepting the AI's output versus acting independently, and belief dynamics were evaluated against Bayesian benchmarks. We find three main results. First, participants do not reset beliefs between tasks: priors in a new task depend on posteriors from the previous task, with a 10-point increase predicting a 3-4 point higher subsequent prior. Second, within tasks, belief updating follows the Bayesian direction but is substantially conservative, proceeding at roughly half the normative Bayesian rate. Third, delegation is driven primarily by subjective beliefs about AI accuracy rather than self-confidence, though confidence independently reduces reliance when beliefs are held constant. Together, these findings show that users form global, path-dependent expectations about multipurpose AI systems, update them conservatively, and rely on AI primarily based on subjective beliefs rather than objective performance. We discuss implications for expectation calibration, reliance design, and the risks of belief spillovers in deployed LLM-based interfaces.

cs.HC↗

arXiv2026

When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption

AI consumer markets are characterized by severe buyer-supplier market asymmetries. Complex AI systems can appear highly accurate while making costly errors or embedding hidden defects. While there have been regulatory efforts surrounding different forms of disclosure, large information gaps remain. This paper provides the first experimental evidence on the important role of information asymmetries and disclosure designs in shaping user adoption of AI systems. We systematically vary the density of low-quality AI systems and the depth of disclosure requirements in a simulated AI product market to gauge how people react to the risk of accidentally relying on a low-quality AI system. Then, we compare participants' choices to a rational Bayesian model, analyzing the degree to which partial information disclosure can improve AI adoption. Our results underscore the deleterious effects of information asymmetries on AI adoption, but also highlight the potential of partial disclosure designs to improve the overall efficiency of human decision-making.

cs.HC↗

arXiv2026

Incentive-Tuning: Understanding and Designing Incentives for Empirical Human-AI Decision-Making Studies

AI has revolutionised decision-making across various fields. Yet human judgement remains paramount for high-stakes decision-making. This has fueled explorations of collaborative decision-making between humans and AI systems, aiming to leverage the strengths of both. To explore this dynamic, researchers conduct empirical studies, investigating how humans use AI assistance for decision-making and how this collaboration impacts results. A critical aspect of conducting these studies is the role of participants, often recruited through crowdsourcing platforms. The validity of these studies hinges on the behaviours of the participants, hence effective incentives that can potentially affect these behaviours are a key part of designing and executing these studies. In this work, we aim to address the critical role of incentive design for conducting empirical human-AI decision-making studies, focusing on understanding, designing, and documenting incentive schemes. Through a thematic review of existing research, we explored the current practices, challenges, and opportunities associated with incentive design for human-AI decision-making empirical studies. We identified recurring patterns, or themes, such as what comprises the components of an incentive scheme, how incentive schemes are manipulated by researchers, and the impact they can have on research outcomes. Leveraging the acquired understanding, we curated a set of guidelines to aid researchers in designing effective incentive schemes for their studies, called the Incentive-Tuning Framework, outlining how researchers can undertake, reflect on, and document the incentive design process. By advocating for a standardised yet flexible approach to incentive design and contributing valuable insights along with practical tools, we hope to pave the way for more reliable and generalizable knowledge in the field of human-AI decision-making.

cs.HC↗

arXiv2026

From SERPs to Sound: How Search Engine Result Pages and AI-generated Podcasts Interact to Influence User Attitudes on Controversial Topics

Compared to search engine result pages (SERPs), AI-generated podcasts represent a relatively new and relatively more passive modality of information consumption, delivering narratives in a naturally engaging format. As these two media increasingly converge in everyday information-seeking behavior, it is essential to explore how their interaction influences user attitudes, particularly in contexts involving controversial, value-laden, and often debated topics. Addressing this need, we aim to understand how information mediums of present-day SERPs and AI-generated podcasts interact to shape the opinions of users. To this end, through a controlled user study (N=483), we investigated user attitudinal effects of consuming information via SERPs and AI-generated podcasts, focusing on how the sequence and modality of exposure shape user opinions. A majority of users in our study corresponded to attitude change outcomes, and we found an effect of sequence on attitude change. Our results further revealed a role of viewpoint bias and the degree of topic controversiality in shaping attitude change, although we found no effect of individual moderators.

cs.IR↗

arXiv2025

Should We Tailor the Talk? Understanding the Impact of Conversational Styles on Preference Elicitation in Conversational Recommender Systems

Conversational recommender systems (CRSs) provide users with an interactive means to express preferences and receive real-time personalized recommendations. The success of these systems is heavily influenced by the preference elicitation process. While existing research mainly focuses on what questions to ask during preference elicitation, there is a notable gap in understanding what role broader interaction patterns including tone, pacing, and level of proactiveness play in supporting users in completing a given task. This study investigates the impact of different conversational styles on preference elicitation, task performance, and user satisfaction with CRSs. We conducted a controlled experiment in the context of scientific literature recommendation, contrasting two distinct conversational styles, high involvement (fast paced, direct, and proactive with frequent prompts) and high considerateness (polite and accommodating, prioritizing clarity and user comfort) alongside a flexible experimental condition where users could switch between the two. Our results indicate that adapting conversational strategies based on user expertise and allowing flexibility between styles can enhance both user satisfaction and the effectiveness of recommendations in CRSs. Overall, our findings hold important implications for the design of future CRSs.

cs.HC↗

arXiv2025

"Even explanations will not help in trusting [this] fundamentally biased system": A Predictive Policing Case-Study

In today's society, where Artificial Intelligence (AI) has gained a vital role, concerns regarding user's trust have garnered significant attention. The use of AI systems in high-risk domains have often led users to either under-trust it, potentially causing inadequate reliance or over-trust it, resulting in over-compliance. Therefore, users must maintain an appropriate level of trust. Past research has indicated that explanations provided by AI systems can enhance user understanding of when to trust or not trust the system. However, the utility of presentation of different explanations forms still remains to be explored especially in high-risk domains. Therefore, this study explores the impact of different explanation types (text, visual, and hybrid) and user expertise (retired police officers and lay users) on establishing appropriate trust in AI-based predictive policing. While we observed that the hybrid form of explanations increased the subjective trust in AI for expert users, it did not led to better decision-making. Furthermore, no form of explanations helped build appropriate trust. The findings of our study emphasize the importance of re-evaluating the use of explanations to build [appropriate] trust in AI based systems especially when the system's use is questionable. Finally, we synthesize potential challenges and policy recommendations based on our results to design for appropriate trust in high-risk based AI-based systems.

cs.HC↗

arXiv2025

Quo Vadis, HCOMP? A Review of 12 Years of Research at the Frontier of Human Computation and Crowdsourcing

The field of human computation and crowdsourcing has historically studied how tasks can be outsourced to humans. However, many tasks previously distributed to human crowds can today be completed by generative AI with human-level abilities, and concerns about crowdworkers increasingly using language models to complete tasks are surfacing. These developments undermine core premises of the field. In this paper, we examine the evolution of the Conference on Human Computation and Crowdsourcing (HCOMP) - a representative example of the field as one of its key venues - through the lens of Kuhn's paradigm shifts. We review 12 years of research at HCOMP, mapping the evolution of HCOMP's research topics and identifying significant shifts over time. Reflecting on the findings through the lens of Kuhn's paradigm shifts, we suggest that these shifts do not constitute a paradigm shift. Ultimately, our analysis of gradual topic shifts over time, combined with data on the evident overlap with related venues, contributes a data-driven perspective to the broader discussion about the future of HCOMP and the field as a whole.

cs.CY↗

arXiv2025

Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages

Recent advances in generative AI have precipitated a proliferation of novel writing assistants. These systems typically rely on multilingual large language models (LLMs), providing globalized workers the ability to revise or create diverse forms of content in different languages. However, there is substantial evidence indicating that the performance of multilingual LLMs varies between languages. Users who employ writing assistance for multiple languages are therefore susceptible to disparate output quality. Importantly, recent research has shown that people tend to generalize algorithmic errors across independent tasks, violating the behavioral axiom of choice independence. In this paper, we analyze whether user utilization of novel writing assistants in a charity advertisement writing task is affected by the AI's performance in a second language. Furthermore, we quantify the extent to which these patterns translate into the persuasiveness of generated charity advertisements, as well as the role of peoples' beliefs about LLM utilization in their donation choices. Our results provide evidence that writers who engage with an LLM-based writing assistant violate choice independence, as prior exposure to a Spanish LLM reduces subsequent utilization of an English LLM. While these patterns do not affect the aggregate persuasiveness of the generated advertisements, people's beliefs about the source of an advertisement (human versus AI) do. In particular, Spanish-speaking female participants who believed that they read an AI-generated advertisement strongly adjusted their donation behavior downwards. Furthermore, people are generally not able to adequately differentiate between human-generated and LLM-generated ads. Our work has important implications for the design, development, integration, and adoption of multilingual LLMs as assistive agents -- particularly in writing tasks.

cs.CL↗

arXiv2025

Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant

Since the explosion in popularity of ChatGPT, large language models (LLMs) have continued to impact our everyday lives. Equipped with external tools that are designed for a specific purpose (e.g., for flight booking or an alarm clock), LLM agents exercise an increasing capability to assist humans in their daily work. Although LLM agents have shown a promising blueprint as daily assistants, there is a limited understanding of how they can provide daily assistance based on planning and sequential decision making capabilities. We draw inspiration from recent work that has highlighted the value of 'LLM-modulo' setups in conjunction with humans-in-the-loop for planning tasks. We conducted an empirical study (N = 248) of LLM agents as daily assistants in six commonly occurring tasks with different levels of risk typically associated with them (e.g., flight ticket booking and credit card payments). To ensure user agency and control over the LLM agent, we adopted LLM agents in a plan-then-execute manner, wherein the agents conducted step-wise planning and step-by-step execution in a simulation environment. We analyzed how user involvement at each stage affects their trust and collaborative team performance. Our findings demonstrate that LLM agents can be a double-edged sword -- (1) they can work well when a high-quality plan and necessary user involvement in execution are available, and (2) users can easily mistrust the LLM agents with plans that seem plausible. We synthesized key insights for using LLM agents as daily assistants to calibrate user trust and achieve better overall task outcomes. Our work has important implications for the future design of daily assistants and human-AI collaboration with LLM agents.

cs.HC↗

arXiv2025

Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant

Explainable artificial intelligence (XAI) methods are being proposed to help interpret and understand how AI systems reach specific predictions. Inspired by prior work on conversational user interfaces, we argue that augmenting existing XAI methods with conversational user interfaces can increase user engagement and boost user understanding of the AI system. In this paper, we explored the impact of a conversational XAI interface on users' understanding of the AI system, their trust, and reliance on the AI system. In comparison to an XAI dashboard, we found that the conversational XAI interface can bring about a better understanding of the AI system among users and higher user trust. However, users of both the XAI dashboard and conversational XAI interfaces showed clear overreliance on the AI system. Enhanced conversations powered by large language model (LLM) agents amplified over-reliance. Based on our findings, we reason that the potential cause of such overreliance is the illusion of explanatory depth that is concomitant with both XAI interfaces. Our findings have important implications for designing effective conversational XAI interfaces to facilitate appropriate reliance and improve human-AI collaboration. Code can be found at https://github.com/delftcrowd/IUI2025_ConvXAI

cs.HC↗

arXiv2025

Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition

In recent years, the rapid development of AI systems has brought about the benefits of intelligent services but also concerns about security and reliability. By fostering appropriate user reliance on an AI system, both complementary team performance and reduced human workload can be achieved. Previous empirical studies have extensively analyzed the impact of factors ranging from task, system, and human behavior on user trust and appropriate reliance in the context of one-step decision making. However, user reliance on AI systems in tasks with complex semantics that require multi-step workflows remains under-explored. Inspired by recent work on task decomposition with large language models, we propose to investigate the impact of a novel Multi-Step Transparent (MST) decision workflow on user reliance behaviors. We conducted an empirical study (N = 233) of AI-assisted decision making in composite fact-checking tasks (i.e., fact-checking tasks that entail multiple sub-fact verification steps). Our findings demonstrate that human-AI collaboration with an MST decision workflow can outperform one-step collaboration in specific contexts (e.g., when advice from an AI system is misleading). Further analysis of the appropriate reliance at fine-grained levels indicates that an MST decision workflow can be effective when users demonstrate a relatively high consideration of the intermediate steps. Our work highlights that there is no one-size-fits-all decision workflow that can help obtain optimal human-AI collaboration. Our insights help deepen the understanding of the role of decision workflows in facilitating appropriate reliance. We synthesize important implications for designing effective means to facilitate appropriate reliance on AI systems in composite tasks, positioning opportunities for the human-centered AI and broader HCI communities.

cs.AI↗