Social media has created new ways for citizens to stay informed on societal matters and participate in political discourse. However, with its algorithmically-curated and virally-propagating content, social media has contributed further to the polarization of opinions by reinforcing users' existing viewpoints. An emerging line of research seeks to understand how content-recommendation algorithms can be re-designed to mitigate societal polarization amplified by social-media interactions. In this paper, we study the problem of allocating seed users to opposing campaigns: by drawing on the equal-time rule of political campaigning on traditional media, our goal is to allocate seed users to campaigners with the aim to maximize the expected number of users who are co-exposed to both campaigns. We show that the problem of maximizing co-exposure is NP-hard and its objective function is neither submodular nor supermodular. However, by exploiting a connection to a submodular function that acts as a lower bound to the objective, we are able to devise a greedy algorithm with provable approximation guarantee. We further provide a scalable instantiation of our approximation algorithm by introducing a novel extension to the notion of random reverse-reachable sets for efficiently estimating the expected co-exposure. We experimentally demonstrate the quality of our proposal on real-world social networks.

In this work, we propose a multi-objective decision making framework that accommodates different user preferences over objectives, where preferences are learned via policy comparisons. Our model consists of a known Markov decision process with a vector-valued reward function, with each user having an unknown preference vector that expresses the relative importance of each objective. The goal is to efficiently compute a near-optimal policy for a given user. We consider two user feedback models. We first address the case where a user is provided with two policies and returns their preferred policy as feedback. We then move to a different user feedback model, where a user is instead provided with two small weighted sets of representative trajectories and selects the preferred one. In both cases, we suggest an algorithm that finds a nearly optimal policy for the user using a number of comparison queries that scales quasilinearly in the number of objectives.

In this work, we propose a multi-objective decision making framework that accommodates different user preferences over objectives, where preferences are learned via policy comparisons. Our model consists of a known Markov decision process with a vector-valued reward function, with each user having an unknown preference vector that expresses the relative importance of each objective. The goal is to efficiently compute a near-optimal policy for a given user. We consider two user feedback models. We first address the case where a user is provided with two policies and returns their preferred policy as feedback. We then move to a different user feedback model, where a user is instead provided with two small weighted sets of representative trajectories and selects the preferred one. In both cases, we suggest an algorithm that finds a nearly optimal policy for the user using a number of comparison queries that scales quasilinearly in the number of objectives.

We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space.

Two-sided marketplaces are standard business models of many online platforms (e.g., Amazon, Facebook, LinkedIn), wherein the platforms have consumers, buyers or content viewers on one side and producers, sellers or content-creators on the other. Consumer side measurement of the impact of a treatment variant can be done via simple online A/B testing. Producer side measurement is more challenging because the producer experience depends on the treatment assignment of the consumers. Existing approaches for producer side measurement are either based on graph cluster-based randomization or on certain treatment propagation assumptions. The former approach results in low-powered experiments as the producer-consumer network density increases and the latter approach lacks a strict notion of error control. In this paper, we propose (i) a quantification of the quality of a producer side experiment design, and (ii) a new experiment design mechanism that generates high-quality experiments based on this quantification.

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient descent, has been the workhorse in protecting user privacy without compromising model accuracy by much. However, applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. To address this issue, we present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.

Generative Retrieval Document retrieval traditionally involved training a 2-tower model which mapped both queries and documents to the same high-dimensional vector space, followed by performing an ANN or MIPS for the query over all the documents to return the closest ones. This technique presents some disadvantages like having a large embedding table [22, 23]. Generative retrieval is a recently proposed technique that aims to fix some of the issues of the traditional approach by producing token by token either the title, name, or the document id string of the document. Cao et al. [5] proposed GENRE for entity retrieval, which used a transformer-based architecture to return, token-by-token, the name of the entity referenced to in a given query. Tay et al. [34] proposed DSI for document retrieval, which was the first system to assign structured semantic DocIDs to each document.

Modern recommender systems perform large-scale retrieval by embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this paper, we propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful tuple of codewords to serve as a Semantic ID for each item. Given Semantic IDs for items in a user session, a Transformer-based sequence-to-sequence model is trained to predict the Semantic ID of the next item that the user will interact with. We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets. In addition, we show that incorporating Semantic IDs into the sequence-to-sequence model enhances its ability to generalize, as evidenced by the improved retrieval performance observed for items with no prior interaction history.

Back in June 2024, Microsoft unexpectedly removed the Windows key C keyboard shortcut for launching the Copilot AI assistant in Windows 11 and replaced it with a dedicated Copilot key on newer keyboards. That was followed up with a Copilot voice chat keyboard shortcut and then later with a "Hey Copilot" verbal launch trigger. As of update KB5058502--the optional May patch that released yesterday for Windows 11 23H2--the Windows key C keyboard shortcut has been reinstated. Tap it to launch Copilot in text chat mode or long-press it to launch Copilot in voice chat mode. A similar update will be released for Windows 11 24H2, reports Windows Latest.