Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 11092 publications
Preview abstract
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent of powerful large language models (LLMs), AI-driven agentic frameworks offer a promising alternative—but their effectiveness remains underexplored. In this paper, we introduce FreshBrew, a novel benchmark for evaluating AI-based agentic frameworks on project-level Java migrations. We benchmark several such frameworks, powered by state-of-the-art LLMs, and compare their performance against established rule-based tools. Our evaluation of AI agents on this benchmark of 228 repositories shows that the top-performing model, Gemini 2.5 Flash, can successfully migrate 56.5% of projects to JDK 17. Our empirical analysis reveals novel insights into the critical strengths and limitations of current agentic approaches, offering actionable insights into their real-world applicability. By releasing FreshBrew publicly upon acceptance, we aim to facilitate rigorous, reproducible evaluation and catalyze progress in AI-driven codebase modernization.
View details
Preview abstract
For many practical applications of quantum computing, the slowest and most costly steps involve coherently accessing classical data. We help address this challenge by applying mass production techniques, which can sometimes allow us to perform operations many times in parallel for a cost that is comparable to a single execution[1-3]. We combine existing mass-production results with modern approaches for loading classical data using ``quantum read-only memory.'' We show that quantum mass production techniques offer no benefit when we consider a cost model that focuses purely on the number of non-Clifford gates. However, analyzing the constant factors in a more nuanced cost model, we find that it may be possible to obtain a reduction in cost of an order or magnitude or more for a variety reasonably-sized fault-tolerant quantum algorithms. We present several applications of quantum mass-production techniques beyond naive parallelization, including a strategy for reducing the cost of serial calls to the same data loading step.
View details
`It’s still abuse’: Community attitudes and perceptions on AI-generated image-based sexual abuse
Nicola Henry
Gemma Beard
Lisa Given
Information, Communication, & Society (2026)
Preview abstract
There are growing concerns about AI-generated image-based sexual abuse (AI-IBSA), also known as nonconsensual sexualized ′deepfakes.′ Empirical research on AI-IBSA, however, remains very limited. This study surveyed 7231 respondents across Australia, the United Kingdom, and the United States to investigate community attitudes and perceptions on AI-IBSA. Through a vignette study, we explored the relationship between public familiarity with AI-IBSA, normative concerns about consent, and context-dependent judgments that vary based on the target's identity relational status, and how the content was used. Our findings reveal strong condemnation of AI-IBSA, yet respondents demonstrated low familiarity with the technology and their views varied depending on particular contexts. AI-IBSA targeting intimate partners was viewed as more unacceptable than targeting celebrities, and content created solely for personal use was seen as less unacceptable than content intended for distribution. The study highlights the need for approaches that go beyond technical fixes and punitive measures, advocating for a multifaceted response that integrates ethical data governance, digital sexual literacy, and restorative justice approaches.
View details
Who Controls the Curriculum for AI? The Limits of Participatory Design for Educational AI
Michael Madaio
Learning Under Algorithmic Conditions, University of Minnesota Press (2026)
Preview abstract
Participatory design is a long-standing effort to shift control over technology design from technologists to users and communities impacted by technologies. For educational AI, this means involving students, families, teachers, and other stakeholders in shaping the design of AI systems. While promising, in this article, I situate the recent calls for participatory design of educational AI systems within a different historical tradition—that of contests over local control of educational curricula. I argue that approaches that attempt to steer the design and development of educational AI through participatory methods may inadvertently reproduce the history of political contestation of educational curricula, in ways that may privilege the most powerful communities, rather than those inequitably impacted. What might it look like to treat participatory AI design as a site for political contestation? How might these approaches avoid reproducing the same majoritarian tendencies that led to educational inequities in the first place?
View details
ALF: Advertiser Large Foundation Model for Multi-Modal Advertiser Understanding
Sunny Rajagopalan
Alireza Golestaneh
Shubhra Chandra
Min Zhou
Jonathan Vronsky
Songbai Yan
2026
Preview abstract
We present ALF (Advertiser Large Foundation model), a multi-modal transformer architecture for understanding advertiser behavior and intent across text, image, video and structured data modalities. Through contrastive learning and multi-task optimization, ALF creates unified advertiser representations that capture both content and behavioral patterns. Our model achieves state-of-the-art performance on critical tasks including fraud detection, policy violation identification, and advertiser similarity matching. In production deployment, ALF reduces false positives by 90\% while maintaining 99.8\% precision on abuse detection tasks. The architecture's effectiveness stems from its novel combination of multi-modal transformations, intersample attention mechanism, spectrally normalized projections, and calibrated probabilistic outputs.
View details
Preview abstract
Semantic data models express high-level business concepts and metrics, capturing the business logic needed to query a database correctly. Most data modeling solutions are built as layers above SQL query engines, with bespoke query languages or APIs. The layered approach means that semantic models can’t be used directly in SQL queries. This paper focuses on an open problem in this space – can we define semantic models in SQL, and make them naturally queryable in SQL?
In parallel, graph query is becoming increasingly popular, including in SQL. SQL/PGQ extends SQL with an embedded subset of the GQL graph query language, adding property graph views and making graph traversal queries easy.
We explore a surprising connection: semantic data models are graphs, and defining graphs is a data modeling problem. In both domains, users start by defining a graph model, and need query language support to easily traverse edges in the graph, which means doing joins in the underlying data.
We propose some useful SQL extensions that make it easier to use higher-level data model abstractions in queries. Users can define a “semantic data graph” view of their data, encapsulating the complex business logic required to query the underlying tables correctly. Then they can query that semantic graph model easily with SQL.
Our SQL extensions are useful independently, simplifying many queries – particularly, queries with joins. We make declared foreign key relationships usable for joins at query time – a feature that seems obvious but is notably missing in standard SQL.
In combination, these extensions provide a practical approach to extend SQL incrementally, bringing semantic modeling and graph query together with the relational model and SQL.
View details
Preview abstract
How many T gates are needed to approximate an arbitrary n-qubit quantum state to within
a given precision ϵ? Improving prior work of Low, Kliuchnikov and Schaeffer, we show that the
optimal asymptotic scaling is Θ(sqrt{2^n log(1/ε)} + log(1/ε)) if we allow an unlimited number of ancilla qubits. We also show that this is the optimal T-count for implementing an arbitrary
diagonal n-qubit unitary to within error ϵ. We describe an application to batched synthesis of
single-qubit unitaries: we can approximate a tensor product of m = O(log log(1/ϵ)) arbitrary
single-qubit unitaries to within error ϵ with the same asymptotic T-count as is required to
approximate just one single-qubit unitary.
View details
A Computer Vision Problem in Flatland
Erin Connelly
Annalisa Crannell
Timothy Duff
Rekha R. Thomas
SIAM Journal on Applied Algebra and Geometry, 10 (2026), pp. 14-45
Preview abstract
When is it possible to project two sets of labeled points of equal cardinality lying in a pair of projective planes to the same image on a projective line? We give a complete answer to this question, obtaining the following results. We first show that such a pair of projections exist if and only if the two point sets are themselves images of a common point set in projective space. Moreover, we find that for generic pairs of point sets, a common projection exists if and only if their cardinality is at most seven. In these cases, we give an explicit description of the loci of projection centers that enable a common image.
View details
CrossCheck: Input Validation for WAN Control Systems
Rishabh Iyer
Isaac Keslassy
Sylvia Ratnasamy
Networked Systems Design and Implementation (NSDI) (2026) (to appear)
Preview abstract
We present CrossCheck, a system that validates inputs to the Software-Defined Networking (SDN) controller in a Wide Area Network (WAN). By detecting incorrect inputs—often stemming from bugs in the SDN control infrastructure—CrossCheck alerts operators before they trigger network outages.
Our analysis at a large-scale WAN operator identifies invalid inputs as a leading cause of major outages, and we show how CrossCheck would have prevented those incidents. We deployed CrossCheck as a shadow validation system for four weeks in a production WAN, during which it accurately detected the single incident of invalid inputs that occurred while sustaining a 0% false positive rate under normal operation, hence imposing little additional burden on operators. In addition, we show through simulation that CrossCheck reliably detects a wide range of invalid inputs (e.g., detecting demand perturbations as small as 5% with 100% accuracy) and maintains a near-zero false positive rate for realistic levels of noisy, missing, or buggy telemetry data (e.g., sustaining zero false positives with up to 30% of corrupted telemetry data).
View details
Preview abstract
A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the first systematic study of faithful confidence calibration of LLMs, benchmarking models' ability to use linguistic expressions of uncertainty that faithfully reflect their intrinsic uncertainty, across a comprehensive array of models, datasets, and prompting strategies. Our results demonstrate that LLMs largely fail at this task, and that existing interventions are insufficient: standard prompt approaches provide only marginal gains, and existing, factuality-based calibration techniques can even harm faithful calibration. To address this critical gap, we introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition. We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness and achieving an 83% win rate over original generations as judged by humans.
View details
Preview abstract
Large Language Models (LLMs) have made it possible for recommendation systems to interact with users in open-ended conversational interfaces. In order to personalize LLM responses, it is crucial to elicit user preferences, especially when there is limited user history. One way to get more information is to present clarifying questions to the user. However, generating effective sequential clarifying questions across various domains remains a challenge, as even advanced LLMs still struggle with this task.
To address this, we introduce a novel approach for training LLMs to ask sequential questions that reveal user preferences. Our method follows a two-stage process inspired by diffusion models: starting from a user profile, in a forward process we generate clarifying questions, obtain answers, and then remove the corresponding information from the user profile, which is analogous to adding noise to the user profile. In the reverse process, zour model learns to “denoise” the user profile by learning to ask effective clarifying questions. Our results show that our method significantly boosts the LLM’s proficiency in asking funnel questions and elicit user preferences effectively.
View details
Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications
Yanxiang Zhang
Zheng Xu
Yuanbo Zhang
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) (2025)
Preview abstract
Error correction is an important capability when applying large language models (LLMs) to facilitate user typing on mobile devices. In this paper, we use LLMs to synthesize a high-quality dataset of error correction pairs to evaluate and improve LLMs for mobile applications. We first prompt LLMs with error correction domain knowledge to build a scalable and reliable addition to the existing data synthesis pipeline. We then adapt the synthetic data distribution to match the mobile application domain by reweighting the samples. The reweighting model is learnt by predicting (a handful of) live A/B test metrics when deploying LLMs in production, given the LLM performance on offline evaluation data and scores from a small privacy-preserving on-device language model. Finally, we present best practices for mixing our synthetic data with other data sources to improve model performance on error correction in both offline evaluation and production live A/B testing.
View details
A Scalable Framework for Evaluating Health Language Models
Neil Mallinar
Tony Faranesh
Brent Winslow
Nova Hammerquist
Ben Graef
Cathy Speed
Mark Malhotra
Shwetak Patel
Xavi Prieto
Daniel McDuff
Ahmed Metwally
(2025)
Preview abstract
Large language models (LLMs) have emerged as powerful tools for analyzing complex datasets. Recent studies demonstrate their potential to generate useful, personalized responses when provided with patient-specific health information that encompasses lifestyle, biomarkers, and context. As LLM-driven health applications are increasingly adopted, rigorous and efficient one-sided evaluation methodologies are crucial to ensure response quality across multiple dimensions, including accuracy, personalization and safety. Current evaluation practices for open-ended text responses heavily rely on human experts. This approach introduces human factors and is often cost-prohibitive, labor-intensive, and hinders scalability, especially in complex domains like healthcare where response assessment necessitates domain expertise and considers multifaceted patient data. In this work, we introduce Adaptive Precise Boolean rubrics: an evaluation framework that streamlines human and automated evaluation of open-ended questions by identifying gaps in model responses using a minimal set of targeted rubrics questions. Our approach is based on recent work in more general evaluation settings that contrasts a smaller set of complex evaluation targets with a larger set of more precise, granular targets answerable with simple boolean responses. We validate this approach in metabolic health, a domain encompassing diabetes, cardiovascular disease, and obesity. Our results demonstrate that Adaptive Precise Boolean rubrics yield higher inter-rater agreement among expert and non-expert human evaluators, and in automated assessments, compared to traditional Likert scales, while requiring approximately half the evaluation time of Likert-based methods. This enhanced efficiency, particularly in automated evaluation and non-expert contributions, paves the way for more extensive and cost-effective evaluation of LLMs in health.
View details
Preview abstract
Text-guided image editing, fueled by recent advancements in generative AI, is becoming increasingly widespread. This trend highlights the need for a comprehensive framework to verify text-guided edits and assess their quality. To address this need, we introduce EditInspector, a novel benchmark for evaluation of text-guided image edits, based on human annotations collected using an extensive template for edit verification. We leverage EditInspector to evaluate the performance of state-of-the-art (SoTA) vision and language models in assessing edits across various dimensions, including accuracy, artifact detection, visual quality, seamless integration with the image scene, adherence to common sense, and the ability to describe edit-induced changes. Our findings indicate that current models struggle to evaluate edits comprehensively and frequently hallucinate when describing the changes. To address these challenges, we propose two novel methods that outperform SoTA models in both artifact detection and difference caption generation.
View details
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren
Jianyi Zhang
Chun-Sung Ferng
Ankur Taly
International Conference on Learning Representations (ICLR) (2025)
Preview abstract
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context from retrieval or the context itself is insufficient to answer the query. To shed light on this, we develop a new notion of sufficient context, along with a method to classify instances that have enough information to answer the query. We then use sufficient context to analyze several models and datasets. By stratifying errors based on context sufficiency, we find that larger models with higher baseline performance (Gemini 1.5 Pro, GPT 4o, Claude 3.5) excel at answering queries when the context is sufficient, but often output incorrect answers instead of abstaining when the context is not. On the other hand, smaller models with lower baseline performance (Llama 3.1, Mistral 3, Gemma 2) hallucinate or abstain often, even with sufficient context. We further categorize cases when the context is useful, and improves accuracy, even though it does not fully answer the query and the model errs without the context. Building on our findings, we explore ways to reduce hallucinations in RAG systems, including a new selective generation method that leverages sufficient context information for guided abstention. Our method improves the fraction of correct answers among times where the model responds by 2--10% for Gemini, GPT, and Gemma.
View details
