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.

people standing in front of a screen with images and a chipboard

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
  • Title
  • Title, descending
  • Year
  • Year, descending
1 - 15 of 10133 publications
    Preview abstract Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the LLMs to generate personalized text. We consider a typical scenario in which the large language model, which generates personalized output, is frozen and can only be accessed through APIs. Under this constraint, all one can do is to improve the input text (i.e., text prompts) sent to the LLM, a procedure that is usually done manually. In this paper, we propose a novel method to automatically revise prompts for personalized text generation. The proposed method takes the initial prompts generated by a state-of-the-art, multistage framework for personalized generation and rewrites a few critical components that summarize and synthesize the personal context. The prompt rewriter employs a training paradigm that chains together supervised learning (SL) and reinforcement learning (RL), where SL reduces the search space of RL and RL facilitates end-to-end training of the rewriter. Using datasets from three representative domains, we demonstrate that the rewritten prompts outperform both the original prompts and the prompts optimized via supervised learning or reinforcement learning alone. In-depth analysis of the rewritten prompts shows that they are not only human readable, but also able to guide manual revision of prompts when there is limited resource to employ reinforcement learning to train the prompt rewriter, or when it is costly to deploy an automatic prompt rewriter for inference. View details
    Preview abstract This paper presents a novel approach to train a direct speech-to-speech translation model from monolingual datasets only in a fully unsupervised manner. The proposed approach combines back-translation, denoising autoencoder, and unsupervised embedding mapping techniques to achieve this goal. We demonstrate the effectiveness of the proposed approach by comparing it against a cascaded baseline using two Spanish and English datasets. The proposed approach achieved a significant improvement over the cascaded baseline on synthesized unpaired conversational and synthesized Common Voice $11$ datasets. View details
    Automatic Speech Recognition of Conversational Speech in Individuals with Disordered Speech
    Bob MacDonald
    Rus Heywood
    Richard Cave
    Katie Seaver
    Antoine Desjardins
    Jordan Green
    Journal of Speech, Language, and Hearing Research (2024) (to appear)
    Preview abstract Purpose: This study examines the effectiveness of automatic speech recognition (ASR) for individuals with speech disorders, addressing the gap in performance between read and conversational ASR. We analyze the factors influencing this disparity and the effect of speech mode-specific training on ASR accuracy. Method: Recordings of read and conversational speech from 27 individuals with various speech disorders were analyzed using both (1) one speaker-independent ASR system trained and optimized for typical speech and (2) multiple ASR models that were personalized to the speech of the participants with disordered speech. Word Error Rates (WERs) were calculated for each speech mode, read vs conversational, and subject. Linear mixed-effect models were used to assess the impact of speech mode and disorder severity on ASR accuracy. We investigated nine variables, classified as technical, linguistic, or speech impairment factors, for their potential influence on the performance gap. Results: We found a significant performance gap between read and conversational speech in both personalized and unadapted ASR models. Speech impairment severity notably impacted recognition accuracy in unadapted models for both speech modes and in personalized models for read speech. Linguistic attributes of utterances were the most influential on accuracy, though atypical speech characteristics also played a role. Including conversational speech samples in model training notably improved recognition accuracy. Conclusions: We observed a significant performance gap in ASR accuracy between read and conversational speech for individuals with speech disorders. This gap was largely due to the linguistic complexity and unique characteristics of speech disorders in conversational speech. Training personalized ASR models using conversational speech significantly improved recognition accuracy, demonstrating the importance of domain-specific training and highlighting the need for further research into ASR systems capable of handling disordered conversational speech effectively. View details
    Preview abstract In this paper we study users' opinions about the privacy of their mobile health apps. We look at what they write in app reviews in the 'Health & Fitness' category on the Google Play store. We identified 2832 apps in this category (based on 1K minimum installs). Using NLP/LLM analyses, we find that 76% of these apps have at least some privacy reviews. In total this yields over 164,000 reviews about privacy, from over 150 countries and in 25 languages. Our analyses identifies top themes and offers an approximation of how widespread these issues are around the world. We show that the top 4 themes - Data Sharing and Exposure, Permission Requests, Location Tracking and Data Collection - are issues of concern in over 70 countries. Our automatically generated thematic summaries reveal interesting aspects that deserve further research around user suspicions (unneeded data collection), user requests (more fine-grained control over data collection and data access), as well as user behavior (uninstalling apps). View details
    Creative ML Assemblages: The Interactive Politics of People, Processes, and Products
    Ramya Malur Srinivasan
    Katharina Burgdorf
    Jennifer Lena
    ACM Conference on Computer Supported Cooperative Work and Social Computing (2024) (to appear)
    Preview abstract Creative ML tools are collaborative systems that afford artistic creativity through their myriad interactive relationships. We propose using ``assemblage thinking" to support analyses of creative ML by approaching it as a system in which the elements of people, organizations, culture, practices, and technology constantly influence each other. We model these interactions as ``coordinating elements" that give rise to the social and political characteristics of a particular creative ML context, and call attention to three dynamic elements of creative ML whose interactions provide unique context for the social impact a particular system as: people, creative processes, and products. As creative assemblages are highly contextual, we present these as analytical concepts that computing researchers can adapt to better understand the functioning of a particular system or phenomena and identify intervention points to foster desired change. This paper contributes to theorizing interactions with AI in the context of art, and how these interactions shape the production of algorithmic art. View details
    Preview abstract While large, generative, multilingual models are rapidly being developed and deployed, their safety and fairness evaluations primarily hinge on resources collected in the English language and some limited translations. This has been demonstrated to be insufficient, and severely lacking in nuances of unsafe language and stereotypes prevalent in different languages and the geographical pockets they are prevalent in. Gathering these resources, at scale, in varied languages and regions also poses a challenge as it requires expansive sociolinguistic knowledge and can also be prohibitively expensive. We utilize an established methodology of coupling LLM generations with distributed annotations to overcome these gaps and create the resource SeeGULL Multilingual, spanning 20 languages across 23 regions. View details
    Preview abstract Relational affect is the affective response (encompassing emotion, expression, feeling) that emerges from an interaction between two people. The case study presented here introduces the concept of relational affect through a human perceptual rating task. Forty-five raters watched short video clips of two people interacting and described their perceived emotion of the individuals and that of the overall interaction. Our qualitative analysis of the rater responses showed that raters used a variety of schemes to reason about emotion, including expressions, context, and perceived appraisal of the event. These reasoning schemes were notably different for perceived individual emotion and relational affect. Our findings show that the vocabulary use for relational affect is distinct from that of individual emotion and relational affect as a phenomenon deepens our understanding of social interactions and moves the field a step closer to realizing the goal of fluid interactions between people and technology. View details
    Preview abstract We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of 512*896 resolution at 8 frames per second. View details
    Preview abstract Referring Image Segmentation is a comprehensive task to segment an object referred by a textual query from an image. In nature, the level of difficulty in this task is affected by the existence of similar objects and the complexity of the referring expression. Recent RIS models still show a significant performance gap between easy and hard scenarios. We pose that the bottleneck exists in the data, and propose a simple but powerful data augmentation method, Negative-mined Mosaic Augmentation (NeMo). This method augments a training image into a mosaic with three other negative images carefully curated by a pretrained multimodal alignment model, e.g., CLIP, to make the sample more challenging. We discover that it is critical to properly adjust the difficulty level, neither too ambiguous nor too trivial. The augmented training data encourages the RIS model to recognize subtle differences and relationships between similar visual entities and to concretely understand the whole expression to locate the right target better. Our approach shows consistent improvements on various datasets and models, verified by extensive experiments. View details
    Preview abstract We're roughly 10 years into the OpenConfig journey. We have implementations in hand from various vendors, and we've gained significant operational experience in the domains of Streaming Telemetry and in Developing Configuration Systems to leverage the developed models. What have we learned? Are the abstractions we've generated the right ones? If not, why? Were we too influenced by the tools and inertia of the time when we made some critical decisions? How do we need to evolve going forward? This discussion is part retrospective/introspective, a candid look at where we've been and what we need to think about as we evolve the next generation of our management (and control) planes. What should we be thinking about as network engineers who write software? View details
    Preview abstract This is an invited OFC 2024 conference workshop talk regarding a new type of lower-power datacenter optics design choice: linear pluggable optics. In this talk I will discuss the fundamental performance constraints facing linear pluggable optics and their implications on DCN and ML use cases View details
    API Governance at Scale
    Mak Ahmad
    JJ Geewax
    David R Karger
    Kwan-Liu Ma
    ICSE 2024 Software Engineering in Practice (2024)
    Preview abstract API Governance, the process of applying standardized sets of policies and guardrails to the design and development of APIs, has only grown in importance and prominence given the continued growth in APIs being produced. In this paper, we present an Action Research style approach to investigate and understand the utility of a multi-faceted API Governance process being adopted inside Google. We first reflect on past research around API Governance, and then introduce three new components, 1. API Improvement Proposals (AIPs) the documented source of truth for API design rules, 2. API Linter, an automated analysis tool which checks for adherence to / violations of AIPs, and 3. API Readability, a program to educate and certify API design experts. These three components are designed to build upon pre-existing processes to scale and improve API design. Through a mixed-methods research strategy, containing both a survey and a series of interviews, we evaluate the utility of these approaches in supporting API Producers. Our research shows that API Producers have positive sentiment towards API Governance, validating the general direction of the program. Specifically, our study participants highlighted the positive impact of API Governance on the quality of the APIs they produced, via consistency in both the outcome and approach. This paper also discusses future research opportunities to enhance API Governance, specifically with regards to newer API Producers, who reported worse sentiment towards the program than their more experienced peers. View details
    AI-powered patching: the future of automated vulnerability fixes
    Jan Keller
    Jan Nowakowski
    Google Security Engineering Technical Report (2024) (to appear)
    Preview abstract As AI continues to advance at rapid speed, so has its ability to unearth hidden security vulnerabilities in all types of software. Every bug uncovered is an opportunity to patch and strengthen code—but as detection continues to improve, we need to be prepared with new automated solutions that bolster our ability to fix those bugs. That’s why our Secure AI Framework (SAIF) includes a fundamental pillar addressing the need to “automate defenses to keep pace with new and existing threats.” This paper shares lessons from our experience leveraging AI to scale our ability to fix bugs, specifically those found by sanitizers in C/C++, Java, and Go code. By automating a pipeline to prompt Large Language Models (LLMs) to generate code fixes for human review, we have harnessed our Gemini model to successfully fix 15% of sanitizer bugs discovered during unit tests, resulting in hundreds of bugs patched. Given the large number of sanitizer bugs found each year, this seemingly modest success rate will with time save significant engineering effort. We expect this success rate to continually improve and anticipate that LLMs can be used to fix bugs in various languages across the software development lifecycle. View details
    Scaling Up LLM Reviews for Google Ads Content Moderation
    Ariel Fuxman
    Chih-Chun Chia
    Dongjin Kwon
    Enming Luo
    Mehmet Tek
    Ranjay Krishna
    Tiantian Fang
    Tushar Dogra
    Yu-Han Lyu
    (2024)
    Preview abstract Large language models (LLMs) are powerful tools for content moderation but LLM inference costs and latency on large volumes of data, such as the Google Ads repository, are prohibitive for their casual usage. This study is focused on scaling up LLM reviews for content moderation in Google Ads. First, we use heuristics to select candidates via filtering and duplicate removal, and create clusters of ads for which we select one representative ad per cluster. Then, LLMs are used to review only the representative ads. Finally we propagate the LLM decisions for representative ads back to their clusters. This method reduces the number of reviews by more than 3 orders of magnitude while achieving a 2x recall compared to a non-LLM model as a baseline. Note that, the success of this approach is a strong function of the representations used in clustering and label propagation; we observed that cross-modal similarity representations yield better results than uni-modal representations. View details
    Conversational AI in health: Design considerations from a Wizard-of-Oz dermatology case study with users, clinicians and a medical LLM
    Brenna Li
    Amy Wang
    Patricia Strachan
    Julie Anne Seguin
    Sami Lachgar
    Karyn Schroeder
    Renee Wong
    Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery, pp. 10
    Preview abstract Although skin concerns are common, access to specialist care is limited. Artificial intelligence (AI)-assisted tools to support medical decisions may provide patients with feedback on their concerns while also helping ensure the most urgent cases are routed to dermatologists. Although AI-based conversational agents have been explored recently, how they are perceived by patients and clinicians is not well understood. We conducted a Wizard-of-Oz study involving 18 participants with real skin concerns. Participants were randomly assigned to interact with either a clinician agent (portrayed by a dermatologist) or an LLM agent (supervised by a dermatologist) via synchronous multimodal chat. In both conditions, participants found the conversation to be helpful in understanding their medical situation and alleviate their concerns. Through qualitative coding of the conversation transcripts, we provide insight on the importance of empathy and effective information-seeking. We conclude with design considerations for future AI-based conversational agents in healthcare settings. View details