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.
Publications
Sort By
1 - 15 of 419 publications
Don’t Interrupt Me – A Large-Scale Study of On-Device Permission Prompt Quieting in Chrome
Marian Harbach
Ravjit Uppal
Andy Paicu
Elias Klim
Balazs Engedy
(2024)
Preview abstract
A recent large-scale experiment conducted by Chrome has demonstrated that a "quieter" web permission prompt can reduce unwanted interruptions while only marginally affecting grant rates. However, the experiment and the partial roll-out were missing two important elements: (1) an effective and context-aware activation mechanism for such a quieter prompt, and (2) an analysis of user attitudes and sentiment towards such an intervention. In this paper, we address these two limitations by means of a novel ML-based activation mechanism -- and its real-world on-device deployment in Chrome -- and a large-scale user study with 13.1k participants from 156 countries. First, the telemetry-based results, computed on more than 20 million samples from Chrome users in-the-wild, indicate that the novel on-device ML-based approach is both extremely precise (>99% post-hoc precision) and has very high coverage (96% recall for notifications permission). Second, our large-scale, in-context user study shows that quieting is often perceived as helpful and does not cause high levels of unease for most respondents.
View details
Websites Need Your Permission Too – User Sentiment and Decision Making on Web Permission Prompts in Desktop Chrome
Marian Harbach
CHI 2024, ACM (to appear)
Preview abstract
The web utilizes permission prompts to moderate access to certain capabilities. We present the first investigation of user behavior and sentiment of this security and privacy measure on the web, using 28 days of telemetry data from more than 100M Chrome installations on desktop platforms and experience sampling responses from 25,706 Chrome users. Based on this data, we find that ignoring and dismissing permission prompts are most common for geolocation and notifications. Permission prompts are perceived as more annoying and interrupting when they are not allowed, and most respondents cite a rational reason for the decision they took. Our data also supports that the perceived availability of contextual information from the requesting website is associated with allowing access to a requested capability. More usable permission controls could facilitate adoption of best practices that address several of the identified challenges; and ultimately could lead to better user experiences and a safer web.
View details
DSI++: Updating Transformer Memory with New Documents
Yi Tay
Jinfeng Rao
Emma Strubell
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Preview abstract
Differentiable Search Indices (DSIs) encode a corpus of documents in model parameters and use the same model to answer user queries directly. Despite the strong performance of DSI models, deploying them in situations where the corpus changes over time is computationally expensive because reindexing the corpus requires re-training the model. In this work, we introduce DSI++, a continual learning challenge for DSI to incrementally index new documents while being able to answer queries related to both previously and newly indexed documents.
Across different model scales and document identifier representations, we show that continual indexing of new documents leads to considerable forgetting of previously indexed documents. We also hypothesize and verify that the model experiences forgetting events during training, leading to unstable learning. To mitigate these issues, we investigate two approaches. The first focuses on modifying the training dynamics. Flatter minima implicitly alleviate forgetting, so we optimize for flatter loss basins and show that the model stably memorizes more documents (+12%). Next, we introduce a generative memory to sample pseudo-queries for documents and supplement them during continual indexing to prevent forgetting for the retrieval task. Extensive experiments on novel continual indexing benchmarks based on Natural Questions (NQ) and MS MARCO demonstrate that our proposed solution mitigates forgetting significantly. Concretely, it improves the average Hits@10 by +21.1% over competitive baselines for NQ and requires 6 times fewer model updates compared to re-training the DSI model for incrementally indexing five corpora in a sequence.
View details
Towards Disentangling Relevance and Bias in Unbiased Learning to Rank
Yunan Zhang
29TH ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (2023)
Preview abstract
Unbiased learning to rank (ULTR) studies the problem of mitigating various biases from implicit user feedback data such as clicks, and has been receiving considerable attention recently. A popular ULTR approach for real-world applications uses a two-tower architecture, where click modeling is factorized into a relevance tower with regular input features, and a bias tower with bias-relevant inputs such as the position of a document. A successful factorization will allow the relevance tower to be exempt from biases. In this work, we identify a critical issue that existing ULTR methods ignored - the bias tower can be confounded with the relevance tower via the underlying true relevance. In particular, the positions were determined by the logging policy, i.e., the previous production model, which would possess relevance information. We give both theoretical analysis and empirical results to show the negative effects on relevance tower due to such a correlation. We then propose two methods to mitigate the negative confounding effects by better disentangling relevance and bias. Offline empirical results on both controlled public datasets and a large-scale industry dataset show the effectiveness of the proposed approaches. We conduct a live experiment on a popular web store for four weeks, and find a significant improvement in user clicks over the baseline, which ignores the negative confounding effect.
View details
Regression Compatible Listwise Objectives for Calibrated Ranking with Binary Relevance
Pratyush Kar
Bing-Rong Lin
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (2023)
Preview abstract
As Learning-to-Rank (LTR) approaches primarily seek to improve ranking quality, their output scores are not scale-calibrated by design. This fundamentally limits LTR usage in score-sensitive applications. Though a simple multi-objective approach that combines a regression and a ranking objective can effectively learn scale-calibrated scores, we argue that the two objectives are not necessarily compatible, which makes the trade-off less ideal for either of them. In this paper, we propose a practical regression compatible ranking (RCR) approach that achieves a better trade-off, where the two ranking and regression components are proved to be mutually aligned. Although the same idea applies to ranking with both binary and graded relevance, we mainly focus on binary labels in this paper. We evaluate the proposed approach on several public LTR benchmarks and show that it consistently achieves either best or competitive result in terms of both regression and ranking metrics, and significantly improves the Pareto frontiers in the context of multi-objective optimization. Furthermore, we evaluated the proposed approach on YouTube Search and found that it not only improved the ranking quality of the production pCTR model, but also brought gains to the click prediction accuracy. The proposed approach has been successfully deployed in the YouTube production system.
View details
Preview abstract
The approximate nearest neighbor (ANN) search problem is fundamental to efficiently serving many real-world machine learning applications. A number of techniques have been developed for ANN search that are efficient, accurate, and scalable. However, such techniques typically have a number of parameters that affect the speed-recall tradeoff, and exhibit poor performance when such parameters aren't properly set. Tuning these parameters has traditionally been a manual process, demanding in-depth knowledge of the underlying search algorithm. This is becoming an increasingly unrealistic demand as ANN search grows in popularity. To tackle this obstacle to ANN adoption, this work proposes a constrained optimization-based approach to tuning quantization-based ANN algorithms. Our technique takes just a desired search cost or recall as input, and then generates tunings that, empirically, are very close to the speed-recall Pareto frontier and give leading performance on standard benchmarks.
View details
Conversational Information Seeking
Hamed Zamani
Johanne R. Trippas
Jeff Dalton
Foundations and Trends® in Information Retrieval (2023), pp. 244-456
Preview abstract
Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is to provide an overview of past research related to CIS, introduce the current state-of-the-art in CIS, highlight the challenges still being faced in the community, and suggest future directions.
View details
HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting
Jiaying Lu
Bo Xiong
Wenjing Ma
Steffen Staab
Carl Yang
Proc. of The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (2023)
Preview abstract
Medical decision-making processes can be enhanced by comprehensive biomedical knowledge bases, which require fusing knowledge graphs constructed from different sources via a uniform index system. The index system often organizes biomedical terms in a hierarchy to provide the aligned entities with fine-grained granularity. To address the challenge of scarce supervision in the biomedical knowledge fusion (BKF) task, researchers have proposed various unsupervised methods. However, these methods heavily rely on ad-hoc lexical and structural matching algorithms, which fail to capture the rich semantics conveyed by biomedical entities and terms. Recently, neural embedding models have proved effective in semantic-rich tasks, but they rely on sufficient labeled data to be adequately trained. To bridge the gap between the scarce-labeled BKF and neural embedding models, we propose HiPrompt, a supervision-efficient knowledge fusion framework that elicits the few-shot reasoning ability of large language models through hierarchy-oriented prompts. Empirical results on the collected KG-Hi-BKF benchmark datasets demonstrate the effectiveness of HiPrompt.
View details
Preview abstract
Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representations), which further optimizes instance-level query representations guided by signals from test-time retrieval results. We leverage a cross-encoder re-ranker to provide fine-grained pseudo labels over retrieval results and iteratively optimize query representations with gradient descent. Our theoretical analysis reveals that TOUR can be viewed as a generalization of the classical Rocchio algorithm for pseudo relevance feedback, and we present two variants that leverage pseudo-labels as hard binary or soft continuous labels. We first apply TOUR on phrase retrieval with our proposed phrase re-ranker, and also evaluate its effectiveness on passage retrieval with an off-the-shelf re-ranker. TOUR greatly improves end-to-end open-domain question answering accuracy, as well as passage retrieval performance. TOUR also consistently improves direct re-ranking by up to 2.0% while running 1.3-2.4x faster with an efficient implementation.
View details
Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
Zhuyun Dai
Tao Lei
Iftekhar Naim
Ming-Wei Chang
Vincent Zhao
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
Preview abstract
Multi-vector retrieval models such as ColBERT [Khattab and Zaharia, 2020] allow token-level interactions between queries and documents, and hence achieve state of the art on many information retrieval benchmarks. However, their non-linear scoring functions are computationally expensive, necessitating a two-stage process for inference: initial candidate retrieval via token retrieval and subsequent refinement stage which re-ranks candidates using the scoring function. Prior training algorithms mainly focus on the re-ranking stage, under-estimating the importance of the token retrieval stage. In this paper, we rethink the role of token retrieval for multi-vector retrieval models and presentXTR, ConteXtualized TokenRetriever. XTR introduces a simple, yet novel, objective function to encourage better token retrieval, which drastically reduce the mismatch between the training objective and the inference procedure. Unexpectedly, our studies have demonstrated that when the token retrieval stage is improved, the refinement stage can be reduced and approximated. Based on this observation, XTR includes a fast refinement algorithm that can re-rank the candidates 4,000× cheaper compared to the refinement stage of ColBERT. On the popular BEIR benchmark [Thakur et al., 2021], XTR advances the state-of-the-art by 3.3 points, achieving 53.2 nDCG@10. Detailed analysis is conducted to confirm that the success of XTR indeed come from better recall of the token-level retrieval stage.
View details
End-to-End Query Term Weighting
Karan Samel
Swaraj Khadanga
Wensong Xu
Xingyu Wang
Kashyap Kolipaka
Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '23) (2023)
Preview abstract
Bag-of-words based lexical retrieval systems are still the most commonly used methods for real-world search applications. Recently deep learning methods have shown promising results to improve this retrieval performance but are expensive to run in an online fashion, non-trivial to integrate into existing production systems, and might not generalize well in out-of-domain retrieval scenarios. Instead, we build on top of lexical retrievers by proposing a Term Weighting BERT (TW-BERT) model. TW-BERT learns to predict the weight for individual n-gram (e.g., uni-grams and bi-grams) query input terms. These inferred weights and terms can be used directly by a retrieval system to perform a query search. To optimize these term weights, TW-BERT incorporates the scoring function used by the search engine, such as BM25, to score query-document pairs. Given sample query-document pairs we can compute a ranking loss over these matching scores, optimizing the learned query term weights in an end-to-end fashion. Aligning TW-BERT with search engine scorers minimizes the changes needed to integrate it into existing production applications, whereas existing deep learning based search methods would require further infrastructure optimization and hardware requirements. The learned weights can be easily utilized by standard lexical retrievers and by other retrieval techniques such as query expansion. We show that TW-BERT improves retrieval performance over strong term weighting baselines within MSMARCO and in out-of-domain retrieval on TREC datasets.
View details
RøB: Ransomware over Modern Web Browsers
Harun Oz
Ahmet Aris
Abbas Acar
Leonardo Babun
Selcuk Uluagac
USENIX Security (2023)
Preview abstract
File System Access (FSA) API enables web applications to
interact with files on the users’ local devices. Even though it
can be used to develop rich web applications, it greatly extends the attack surface, which can be abused by adversaries
to cause significant harm. In this paper, for the first time in the
literature, we extensively study this new attack vector that can
be used to develop a powerful new ransomware strain over
a browser. Using the FSA API and WebAssembly technology, we demonstrate this novel browser-based ransomware
called RØB as a malicious web application that encrypts the
user’s files from the browser. We use RØB to perform impact
analysis with different OSs, local directories, and antivirus solutions as well as to develop mitigation techniques against it.
Our evaluations show that RØB can encrypt the victim’s local
files including cloud-integrated directories, external storage
devices, and network-shared folders regardless of the access
limitations imposed by the API. Moreover, we evaluate and
show how the existing defense solutions fall short against
RØB in terms of their feasibility. We propose three potential
defense solutions to mitigate this new attack vector. These
solutions operate at different levels (i.e., browser-level, filesystem-level, and user-level) and are orthogonal to each other.
Our work strives to raise awareness of the dangers of RØBlike browser-based ransomware strains and shows that the
emerging API documentation (in this case the popular FSA)
can be equivocal in terms of reflecting the extent of the threat.
View details
SparseEmbed: Learning Sparse Lexical Representations with Contextual Embeddings for Retrieval
Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '23), ACM (2023) (to appear)
Preview abstract
In dense retrieval, prior work has largely improved retrieval effectiveness using multi-vector dense representations, exemplified by ColBERT. In sparse retrieval, more recent work, such as SPLADE, demonstrated that one can also learn sparse lexical representations to achieve comparable effectiveness while enjoying better interpretability. In this work, we combine the strengths of both the sparse and dense representations for first-stage retrieval. Specifically, we propose SparseEmbed – a novel retrieval model that learns sparse lexical representations with contextual embeddings. Compared with SPLADE, our model leverages the contextual embeddings to improve model expressiveness. Compared with ColBERT, our sparse representations are trained end-to-end to optimize both efficiency and effectiveness.
View details
The Capable Web
ACM, Austin, TX, USA
Preview abstract
In this paper, I discuss arguments in favor and in disfavor of building for the Web. I look at three extraordinary examples of apps built for the Web, and analyze reasons their creators provided for doing so. In continuation, I look at the decline of interest in cross-platform app frameworks with the exception of Flutter, which leads me to the two research questions (i) "Why do people not fully bet on PWA" and (ii) "Why is Flutter so popular". My hypothesis for why developers don’t more frequently set on the Web is that in many cases they (or their non-technical reporting lines) don’t realize how powerful it has become. To counter that, I introduce a Web app and a browser extension that demonstrate the Web’s capabilities.
View details
1-Pager: One Pass Answer Generation and Evidence Retrieval
Palak Jain
The 2023 Conference on Empirical Methods in Natural Language Processing (2023) (to appear)
Preview abstract
We present 1-PAGER the first system that answers a question and retrieves evidence using
a single Transformer-based model and decoding process. 1-PAGER incrementally partitions
the retrieval corpus using constrained decoding to select a document and answer string,
and we show that this is competitive with comparable retrieve-and-read alternatives according to both retrieval and answer accuracy metrics. 1-PAGER also outperforms the equivalent ‘closed-book’ question answering model,
by grounding predictions in an evidence corpus. While 1-PAGER is not yet on-par with
more expensive systems that read many more
documents before generating an answer, we argue that it provides an important step toward
attributed generation by folding retrieval into
the sequence-to-sequence paradigm that is currently dominant in NLP. We also show that the
search paths used to partition the corpus are
easy to read and understand, paving a way forward for interpretable neural retrieval.
View details
