One thing seems for sure: people are not ready for "digital workers" just yet. That's the lesson learned by Sarah Franklin, the CEO of Lattice, a human resources and performance management platform that offers performance coaching, talent reviews, onboarding automation, compensation management and a host of other HR tools to more than 5,000 organizations around the world. What is a digital employee? According to Franklin, it's avatars like Devin the engineer, Harvey the lawyer, Einstein the service agent and Piper the sales agent who have "entered the workforce and become our colleagues". But these are not real workers.

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling the attribution task as preference learning and introducing an Automatic Preference Optimization (APO) framework. First, we create a curated collection for post-training with 6,330 examples by collecting and filtering from existing datasets. Second, considering the high cost of labelling preference data, we further propose an automatic method to synthesize attribution preference data resulting in 95,263 pairs. Moreover, inspired by the human citation process, we further propose a progressive preference optimization method by leveraging fine-grained information. Extensive experiments on three datasets (i.e., ASQA, StrategyQA, and ELI5) demonstrate that APO achieves state-of-the-art citation F1 with higher answer quality.

The potential of using a large language model (LLM) as a knowledge base (KB) has sparked significant interest. To manage the knowledge acquired by LLMs, we need to ensure that the editing of learned facts respects internal logical constraints, which are known as dependency of knowledge. Existing work on editing LLMs has partially addressed the issue of dependency, when the editing of a fact should apply to its lexical variations without disrupting irrelevant ones. However, they neglect the dependency between a fact and its logical implications. We propose an evaluation protocol with an accompanying question-answering dataset, DepEdit, that provides a comprehensive assessment of the editing process considering the above notions of dependency. Our protocol involves setting up a controlled environment in which we edit facts and monitor their impact on LLMs, along with their implications based on If-Then rules. Extensive experiments on DepEdit show that existing knowledge editing methods are sensitive to the surface form of knowledge, and that they have limited performance in inferring the implications of edited facts.

This paper introduces Track Mix, a personalized playlist generation system released in 2022 on the music streaming service Deezer. Track Mix automatically generates "mix" playlists inspired by initial music tracks, allowing users to discover music similar to their favorite content. To generate these mixes, we consider a Transformer model trained on millions of track sequences from user playlists. In light of the growing popularity of Transformers in recent years, we analyze the advantages, drawbacks, and technical challenges of using such a model for mix generation on the service, compared to a more traditional collaborative filtering approach. Since its release, Track Mix has been generating playlists for millions of users daily, enhancing their music discovery experience on Deezer.

Artificial intelligence (AI) is becoming ubiquitous. It provides directions while we drive, answers our questions, offers music recommendations and powers a growing number of business processes in the workplace. In fact, AI is working its way into so many aspects of our personal and professional lives that my company has begun to refer to it as "everyday AI." Soon, I'd argue, it will become as ubiquitous -- and necessary -- as electricity. Yet, despite the progress, we've only scratched the surface in the potential ways that AI can, and no doubt will, change business and the world. Gartner has forecast that it will take until 2025 for half of organizations worldwide to reach what Gartner's AI maturity model describes as the "stabilization stage" of AI maturity or beyond.

Artificial intelligence (AI) is becoming ubiquitous. It provides directions while we drive, answers our questions, offers music recommendations and powers a growing number of business processes in the workplace. In fact, AI is working its way into so many aspects of our personal and professional lives that my company has begun to refer to it as "everyday AI." Soon, I'd argue, it will become as ubiquitous -- and necessary -- as electricity. Yet, despite the progress, we've only scratched the surface in the potential ways that AI can, and no doubt will, change business and the world. Gartner has forecast that it will take until 2025 for half of organizations worldwide to reach what Gartner's AI maturity model describes as the "stabilization stage" of AI maturity or beyond.

On a May evening in 1959, C.P. Snow, a popular novelist and former research scientist, gave a lecture before a gathering of dons and students at the University of Cambridge, his alma mater. He called his talk "The Two Cultures and the Scientific Revolution." Snow declared that a gulf of mutual incomprehension divided literary intellectuals and scientists. "The non-scientists have a rooted impression that the scientists are shallowly optimistic, unaware of man's condition," Snow said. "On the other hand, the scientists believe that the literary intellectuals are totally lacking in foresight, peculiarly unconcerned with their brother men, in a deep sense anti-intellectual, anxious to restrict both art and thought to the existential moment." Snow didn't expect much of his talk.

That's what often happens when people take on debt. Shakespeare famously warned us about the dangers of going into debt, stating that "neither a borrower nor a lender is; for loan doth oft lose both itself and friend." For some people that become swamped by debt, they find themselves sinking into an all-encompassing abyss. The debt impacts them, their loved ones, their friends and acquaintances, and otherwise bodes for indubitably rotten tidings. Sometimes, a person is oblivious to their mounting debt. I know that seems nearly impossible to imagine. What can happen is that the person starts making zillions of charges on their credit cards, and they meanwhile delude themselves into not realizing there will ultimately be unfavorable consequences. The piper, though, will eventually need to be paid. Credit card agencies often make life especially easy for those that wantonly are apt to spend.

Kellye Franklin recalls the devastation when her now 81-year-old father, a loyal air force veteran, tried to make his own breakfast one morning. Seven boxes of open cereal on the living room floor with milk poured directly into every one of them. He would later be diagnosed with moderate to severe dementia. Yet Franklin, 39, who is her dad's only child and his primary caregiver, does not worry about that repeating now. In late 2019, she had motion sensors that are connected to an artificial intelligence (AI) system installed in the two-floor townhome she and her dad share in Inglewood, in Los Angeles county.

Advanced persistent threats (APT) are stealthy cyber-attacks that are aimed at stealing valuable information from target organizations and tend to extend in time. Blocking all APTs is impossible, security experts caution, hence the importance of research on early detection and damage limitation. Whole-system provenance-tracking and provenance trace mining are considered promising as they can help find causal relationships between activities and flag suspicious event sequences as they occur. We introduce an unsupervised method that exploits OS-independent features reflecting process activity to detect realistic APT-like attacks from provenance traces. Anomalous processes are ranked using both frequent and rare event associations learned from traces. Results are then presented as implications which, since interpretable, help leverage causality in explaining the detected anomalies. When evaluated on Transparent Computing program datasets (DARPA), our method outperformed competing approaches.