arXiv subjects

Shirley Zhang

Publications and source records attributed to Shirley Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Level Aggregation via Dual Fitting: An $O(D)$-Competitive Algorithm

We present a new online algorithm for the well-known Multi-Level Aggregation Problem (MLAP) with arbitrary delay functions, achieving a $2D$-competitive ratio, where $D$ is the depth of the underlying tree. This result improves the current best-known competitive ratio of $O(D^2)$ and asymptotically matches the $D$-competitive bound previously known only for the deadline variant, thereby closing the asymptotic gap between the two settings. Our key technical contribution is a novel dual fitting framework that provides a unified analysis for both settings; in particular, it also establishes a $D$-competitive ratio for MLAP with deadlines. Our analysis is built upon two new ideas: a hindsight dual construction, which resolves the infeasibility issues in traditional online primal-dual methods, and a time-dependent dual packing that maintains feasibility over dynamic request sets.

cs.DS↗

arXiv2026

AI Alignment From Social Choice Perspectives

Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflicting views of desirable behavior, the learned objective becomes an aggregate determination of what the model should prefer. We survey recent work that has studied this aggregation problem through the lens of social choice theory. We illustrate how the social choice perspective helps identify failure modes in the feedback aggregation layer and reveals a broader design space for handling disagreement in explicit and principled ways.

cs.AI↗

arXiv2026

Finding Common Ground in a Sea of Alternatives

We study the problem of selecting a statement that finds common ground across diverse population preferences. Generative AI is uniquely suited for this task because it can access a practically infinite set of statements, but AI systems like the Habermas machine leave the choice of generated statement to a voting rule. What it means for this rule to find common ground, however, is not well-defined. In this work, we propose a formal model for finding common ground in the infinite alternative setting based on the proportional veto core from social choice. To provide guarantees relative to these infinitely many alternatives and a large population, we wish to satisfy a notion of proportional veto core using only query access to the unknown distribution of alternatives and voters. We design an efficient sampling-based algorithm that returns an alternative in the (approximate) proportional veto core with high probability and prove matching lower bounds, which show that no algorithm can do the same using fewer queries. On a synthetic dataset of preferences over text, we confirm the effectiveness of our sampling-based algorithm and compare other social choice methods as well as LLM-based methods in terms of how reliably they produce statements in the proportional veto core.

cs.GT↗

arXiv2026

"It's like a pet...but my pet doesn't collect data about me": Multi-person Households' Privacy Design Preferences for Household Robots

Household robots boasting mobility, more sophisticated sensors, and powerful processing models have become increasingly prevalent in the commercial market. However, these features may expose users to unwanted privacy risks, including unsolicited data collection and unauthorized data sharing. While security and privacy researchers thus far have explored people's privacy concerns around household robots, literature investigating people's preferred privacy designs and mitigation strategies is still limited. Additionally, the existing literature has not yet accounted for multi-user perspectives on privacy design and household robots. We aimed to fill this gap by conducting in-person participatory design sessions with 15 households to explore how they would design a privacy-aware household robot based on their concerns and expectations. We found that participants did not trust that robots, or their respective manufacturers, would respect the data privacy of household members or operate in a multi-user ecosystem without jeopardizing users' personal data. Based on these concerns, they generated designs that gave them authority over their data, contained accessible controls and notification systems, and could be customized and tailored to suit the needs and preferences of each user over time. We synthesize our findings into actionable design recommendations for robot manufacturers and developers.

cs.HC↗

arXiv2026

Truthful Fair Division under Stochastic Valuations

We study no-money mechanisms for allocating indivisible items to strategic agents with additive preferences under a stochastic model. In this model, items' values are drawn from an underlying distribution and mechanisms are evaluated with respect to this draw (e.g., in expectation, or with high probability). Motivated by worst-case impossibilities which show that truthfulness severely restricts fairness and efficiency, we ask whether truthful mechanisms continue to perform poorly on random instances. We first focus on dominant-strategy incentive compatible (DSIC) mechanisms. For two agents, we obtain a tight picture. Specifically, we show that there exists a distribution under which no DSIC mechanism achieves an expected welfare approximation better than $\frac{2+\sqrt{2}}{4}\approx 0.854$, and we give a DSIC mechanism that matches this bound for all distributions simultaneously. We further show that, for every distribution, there exists a DSIC mechanism that is envy-free with high probability and obtains the same welfare. A key ingredient is a new, tight connection between welfare guarantees of a family of DSIC, no-money mechanisms and i.i.d.\ prophet inequalities. This connection allows us to generalize to $n$ agents; in particular, we obtain a DSIC mechanism that achieves a $\approx 0.745$ approximation to welfare, and another DSIC mechanism achieving a $1/2$-approximation welfare that is envy-free with high probability. We then turn to Bayesian incentive compatibility (BIC). Under i.i.d.\ valuations, we show that BIC comes at essentially no cost: we design a prior-independent BIC mechanism that achieves a $(1-\varepsilon)$-approximation to the optimal welfare, while being envy-free with high probability. Under independent but non-identical priors, we obtain BIC mechanisms that are $(1-\varepsilon)$-approximately Pareto efficient and envy-free with high probability.

cs.GT↗

arXiv2025

Benchmarking LLM Privacy Recognition for Social Robot Decision Making

While robots have previously utilized rule-based systems or probabilistic models for user interaction, the rapid evolution of large language models (LLMs) presents new opportunities to develop LLM-powered robots for enhanced human-robot interaction (HRI). To fully realize these capabilities, however, robots need to collect data such as audio, fine-grained images, video, and locations. As a result, LLMs often process sensitive personal information, particularly within private environments, such as homes. Given the tension between utility and privacy risks, evaluating how current LLMs manage sensitive data is critical. Specifically, we aim to explore the extent to which out-of-the-box LLMs are privacy-aware in the context of household robots. In this work, we present a set of privacy-relevant scenarios developed using the Contextual Integrity (CI) framework. We first surveyed users' privacy preferences regarding in-home robot behaviors and then examined how their privacy orientations affected their choices of these behaviors (N = 450). We then provided the same set of scenarios and questions to state-of-the-art LLMs (N = 10) and found that the agreement between humans and LLMs was generally low. To further investigate the capabilities of LLMs as potential privacy controllers, we implemented four additional prompting strategies and compared their results. We discuss the performance of the evaluated models as well as the implications and potential of AI privacy awareness in human-robot interaction.

cs.RO↗

arXiv2025

Metritocracy: Representative Metrics for Lite Benchmarks

A common problem in LLM evaluation is how to choose a subset of metrics from a full suite of possible metrics. Subset selection is usually done for efficiency or interpretability reasons, and the goal is often to select a ``representative'' subset of metrics. However, ``representative'' is rarely clearly defined. In this work, we use ideas from social choice theory to formalize two notions of representation for the selection of a subset of evaluation metrics. We first introduce positional representation, which guarantees every alternative is sufficiently represented at every position cutoff. We then introduce positional proportionality, which guarantees no alternative is proportionally over- or under-represented by more than a small error at any position. We prove upper and lower bounds on the smallest number of metrics needed to guarantee either of these properties in the worst case. We also study a generalized form of each property that allows for additional input on groups of metrics that must be represented. Finally, we tie theory to practice through real-world case studies on both LLM evaluation and hospital quality evaluation.

cs.LG↗

arXiv2025

Exploring Families' Use and Mediation of Generative AI: A Multi-User Perspective

Generative AI (GenAI) platforms, such as ChatGPT, have gained popularity among the public due to their ease of access, use, and support of educational and creative activities. Despite these benefits, GenAI poses unique risks for families, such as lacking sufficient safeguards tailored to protect children under 13 years of age and not offering parental control features. This study explores how parents mediate their children's use of GenAI and the factors/processes that shape this mediation. Through analyzing semi-structured interviews with 12 families, we identified ways in which families used and mediated GenAI and factors that influenced parents' GenAI mediation strategies. We contextualize our findings with a modified model of family mediation strategies, drawing from previous family media and mediation frameworks. We provide insights for future research on Family-GenAI interactions and highlight the need for more robust protective measures on GenAI platforms for families.

cs.HC↗

arXiv2025

"Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications

Machine learning models deployed locally on social media applications are used for features, such as face filters which read faces in-real time, and they expose sensitive attributes to the apps. However, the deployment of machine learning models, e.g., when, where, and how they are used, in social media applications is opaque to users. We aim to address this inconsistency and investigate how social media user perceptions and behaviors change once exposed to these models. We conducted user studies (N=21) and found that participants were unaware to both what the models output and when the models were used in Instagram and TikTok, two major social media platforms. In response to being exposed to the models' functionality, we observed long term behavior changes in 8 participants. Our analysis uncovers the challenges and opportunities in providing transparency for machine learning models that interact with local user data.

cs.HC↗

arXiv2025

Clone-Robust AI Alignment

A key challenge in training Large Language Models (LLMs) is properly aligning them with human preferences. Reinforcement Learning with Human Feedback (RLHF) uses pairwise comparisons from human annotators to train reward functions and has emerged as a popular alignment method. However, input datasets in RLHF are not necessarily balanced in the types of questions and answers that are included. Therefore, we want RLHF algorithms to perform well even when the set of alternatives is not uniformly distributed. Drawing on insights from social choice theory, we introduce robustness to approximate clones, a desirable property of RLHF algorithms which requires that adding near-duplicate alternatives does not significantly change the learned reward function. We first demonstrate that the standard RLHF algorithm based on regularized maximum likelihood estimation (MLE) fails to satisfy this property. We then propose the weighted MLE, a new RLHF algorithm that modifies the standard regularized MLE by weighting alternatives based on their similarity to other alternatives. This new algorithm guarantees robustness to approximate clones while preserving desirable theoretical properties.

cs.LG↗

arXiv2025

Improved Regret Bounds for Online Fair Division with Bandit Learning

We study online fair division when there are a finite number of item types and the player values for the items are drawn randomly from distributions with unknown means. In this setting, a sequence of indivisible items arrives according to a random online process, and each item must be allocated to a single player. The goal is to maximize expected social welfare while maintaining that the allocation satisfies proportionality in expectation. When player values are normalized, we show that it is possible to with high probability guarantee proportionality constraint satisfaction and achieve $\tilde{O}(\sqrt{T})$ regret. To achieve this result, we present an upper confidence bound (UCB) algorithm that uses two rounds of linear optimization. This algorithm highlights fundamental aspects of proportionality constraints that allow for a UCB algorithm despite the presence of many (potentially tight) constraints. This result improves upon the previous best regret rate of $\tilde{O}(T^{2/3})$.

cs.GT↗

arXiv2025

Multi-Apartment Rent Division

Rent division is the well-studied problem of fairly assigning rooms and dividing rent among a set of roommates within a single apartment. A shortcoming of existing solutions is that renters are assumed to be considering apartments in isolation, whereas in reality, renters can choose among multiple apartments. In this paper, we generalize the rent division problem to the multi-apartment setting, where the goal is to both fairly choose an apartment among a set of alternatives and fairly assign rooms and rents within the chosen apartment. Our main contribution is a generalization of envy-freeness called negotiated envy-freeness. We show that a solution satisfying negotiated envy-freeness is guaranteed to exist and that it is possible to optimize over all negotiated envy-free solutions in polynomial time. We also define an even stronger fairness notion called universal envy-freeness and study its existence when values are drawn randomly.

cs.GT↗

arXiv2024

Honor Among Bandits: No-Regret Learning for Online Fair Division

We consider the problem of online fair division of indivisible goods to players when there are a finite number of types of goods and player values are drawn from distributions with unknown means. Our goal is to maximize social welfare subject to allocating the goods fairly in expectation. When a player's value for an item is unknown at the time of allocation, we show that this problem reduces to a variant of (stochastic) multi-armed bandits, where there exists an arm for each player's value for each type of good. At each time step, we choose a distribution over arms which determines how the next item is allocated. We consider two sets of fairness constraints for this problem: envy-freeness in expectation and proportionality in expectation. Our main result is the design of an explore-then-commit algorithm that achieves $\tilde{O}(T^{2/3})$ regret while maintaining either fairness constraint. This result relies on unique properties fundamental to fair-division constraints that allow faster rates of learning, despite the restricted action space. We also prove a lower bound of $\tildeΩ(T^{2/3})$ regret for our setting, showing that our results are tight.

cs.GT↗

arXiv2024

Automatically Detecting Online Deceptive Patterns

Deceptive patterns in digital interfaces manipulate users into making unintended decisions, exploiting cognitive biases and psychological vulnerabilities. These patterns have become ubiquitous on various digital platforms. While efforts to mitigate deceptive patterns have emerged from legal and technical perspectives, a significant gap remains in creating usable and scalable solutions. We introduce our AutoBot framework to address this gap and help web stakeholders navigate and mitigate online deceptive patterns. AutoBot accurately identifies and localizes deceptive patterns from a screenshot of a website without relying on the underlying HTML code. AutoBot employs a two-stage pipeline that leverages the capabilities of specialized vision models to analyze website screenshots, identify interactive elements, and extract textual features. Next, using a large language model, AutoBot understands the context surrounding these elements to determine the presence of deceptive patterns. We also use AutoBot, to create a synthetic dataset to distill knowledge from 'teacher' LLMs to smaller language models. Through extensive evaluation, we demonstrate AutoBot's effectiveness in detecting deceptive patterns on the web, achieving an F1-score of 0.93 when detecting deceptive patterns, underscoring its potential as an essential tool for mitigating online deceptive patterns. We implement AutoBot, across three downstream applications targeting different web stakeholders: (1) a local browser extension providing users with real-time feedback, (2) a Lighthouse audit to inform developers of potential deceptive patterns on their sites, and (3) as a measurement tool designed for researchers and regulators.

cs.HC↗

arXiv2024

Multi-District School Choice: Playing on Several Fields

We extend the seminal model of Pathak and S\"onmez (2008) to a setting with multiple school districts, each running its own separate centralized match, and focus on the case of two districts. In our setting, in addition to each student being either sincere or sophisticated, she is also either constrained - able to apply only to schools within her own district of residence - or unconstrained - able to choose any single district within which to apply. We show that several key results from Pathak and S\"onmez (2008) qualitatively flip: A sophisticated student may prefer for a sincere student to become sophisticated, and a sophisticated student may prefer for her own district to use Deferred Acceptance over the Boston Mechanism, irrespective of the mechanism used by the other district. We furthermore investigate the preferences of students over the constraint levels of other students. Many of these phenomena appear abundantly in large random markets.

cs.GT↗

arXiv2024

Online Flexible Busy Time Scheduling on Heterogeneous Machines

We study the online busy time scheduling model on heterogeneous machines. In our setting, jobs with uniform length arrive online with a deadline that becomes known to the algorithm at the job's arrival time. An algorithm has access to machines, each with different associated capacities and costs. The goal is to schedule jobs on machines by their deadline, so that the total cost incurred by the scheduling algorithm is minimized. While busy time scheduling has been well-studied, relatively little is known when machines are heterogeneous (i.e., have different costs and capacities), despite this natural theoretical generalization being the most practical model for clients using cloud computing services. We make significant progress in understanding this model by designing an 8-competitive algorithm for the problem on unit-length jobs and providing a lower bound of 2 on the competitive ratio. The lower bound is tight in the setting when jobs form non-nested intervals. Our 8-competitive algorithm generalizes to one with competitive ratio $8(2p-1)/p < 16$ when all jobs have uniform length $p$.

cs.DS↗

arXiv2023

The Distortion of Binomial Voting Defies Expectation

In computational social choice, the distortion of a voting rule quantifies the degree to which the rule overcomes limited preference information to select a socially desirable outcome. This concept has been investigated extensively, but only through a worst-case lens. Instead, we study the expected distortion of voting rules with respect to an underlying distribution over voter utilities. Our main contribution is the design and analysis of a novel and intuitive rule, binomial voting, which provides strong distribution-independent guarantees for both expected distortion and expected welfare.

cs.GT↗

arXiv2023

Selling to Multiple No-Regret Buyers

We consider the problem of repeatedly auctioning a single item to multiple i.i.d buyers who each use a no-regret learning algorithm to bid over time. In particular, we study the seller's optimal revenue, if they know that the buyers are no-regret learners (but only that their behavior satisfies some no-regret property -- they do not know the precise algorithm/heuristic used). Our main result designs an auction that extracts revenue equal to the full expected welfare whenever the buyers are "mean-based" (a property satisfied by standard no-regret learning algorithms such as Multiplicative Weights, Follow-the-Perturbed-Leader, etc.). This extends a main result of [BMSW18] which held only for a single buyer. Our other results consider the case when buyers are mean-based but never overbid. On this front, [BMSW18] provides a simple LP formulation for the revenue-maximizing auction for a single-buyer. We identify several formal barriers to extending this approach to multiple buyers.

cs.GT↗