Amidst decline in public trust in technology, computing ethics have taken center stage, and critics have raised questions about corporate ethics washing. Yet few studies examine the actual implementation of AI ethics values in technology companies. Based on a qualitative analysis of technology workers tasked with integrating AI ethics into product development, we find that workers experience an environment where policies, practices, and outcomes are decoupled. We analyze AI ethics workers as ethics entrepreneurs who work to institutionalize new ethics-related practices within organizations. We show that ethics entrepreneurs face three major barriers to their work. First, they struggle to have ethics prioritized in an environment centered around software product launches. Second, ethics are difficult to quantify in a context where company goals are incentivized by metrics. Third, the frequent reorganization of teams makes it difficult to access knowledge and maintain relationships central to their work. Consequently, individuals take on great personal risk when raising ethics issues, especially when they come from marginalized backgrounds. These findings shed light on complex dynamics of institutional change at technology companies.

Applications of large open-domain knowledge graphs (KGs) to real-world problems pose many unique challenges. In this paper, we present extensions to Saga our platform for continuous construction and serving of knowledge at scale. In particular, we describe a pipeline for training knowledge graph embeddings that powers key capabilities such as fact ranking, fact verification, a related entities service, and support for entity linking. We then describe how our platform, including graph embeddings, can be leveraged to create a Semantic Annotation service that links unstructured Web documents to entities in our KG. Semantic annotation of the Web effectively expands our knowledge graph with edges to open-domain Web content which can be used in various search and ranking problems. Finally, we leverage annotated Web documents to drive Open-domain Knowledge Extraction. This targeted extraction framework identifies important coverage issues in the KG, then finds relevant data sources for target entities on the Web and extracts missing information to enrich the KG. Finally, we describe adaptations to our knowledge platform needed to construct and serve private personal knowledge on-device. This includes private incremental KG construction, cross-device knowledge sync, and global knowledge enrichment.

Diffusion models have experienced a surge of interest as highly expressive yet efficiently trainable probabilistic models. We show that these models are an excellent fit for synthesising human motion that co-occurs with audio, e.g., dancing and co-speech gesticulation, since motion is complex and highly ambiguous given audio, calling for a probabilistic description. Specifically, we adapt the DiffWave architecture to model 3D pose sequences, putting Conformers in place of dilated convolutions for improved modelling power. We also demonstrate control over motion style, using classifier-free guidance to adjust the strength of the stylistic expression. Experiments on gesture and dance generation confirm that the proposed method achieves top-of-the-line motion quality, with distinctive styles whose expression can be made more or less pronounced. We also synthesise path-driven locomotion using the same model architecture. Finally, we generalise the guidance procedure to obtain product-of-expert ensembles of diffusion models and demonstrate how these may be used for, e.g., style interpolation, a contribution we believe is of independent interest. See https://www.speech.kth.se/research/listen-denoise-action/ for video examples, data, and code.

Denoising Diffusion Probabilistic Models (DDPMs) have made great strides in generating high-quality samples in both discrete and continuous domains. However, Discrete DDPMs (D3PMs) have yet to be applied to the domain of Symbolic Music. This work presents the direct generation of Polyphonic Symbolic Music using D3PMs. Our model exhibits state-of-the-art sample quality, according to current quantitative evaluation metrics, and allows for flexible infilling at the note level. We further show, that our models are accessible to post-hoc classifier guidance, widening the scope of possible applications. However, we also cast a critical view on quantitative evaluation of music sample quality via statistical metrics, and present a simple algorithm that can confound our metrics with completely spurious, non-musical samples.

Open-Domain Question Answering (ODQA) aims at answering factoid questions without explicitly providing specific background documents. In a zero-shot setting, this task is more challenging since no data is available to train customized models like Retriever-Readers. Recently, Large Language Models (LLMs) like GPT-3 have shown their power in zero-shot ODQA with direct prompting methods, but these methods are still far from releasing the full powerfulness of LLMs only in an implicitly invoking way. In this paper, we propose a Self-Prompting framework to explicitly utilize the massive knowledge stored in the parameters of LLMs and their strong instruction understanding abilities. Concretely, we prompt LLMs step by step to generate multiple pseudo QA pairs with background passages and explanations from scratch and then use those generated elements for in-context learning. Experimental results show our method surpasses previous SOTA methods significantly on three widely-used ODQA datasets, and even achieves comparable performance with some Retriever-Reader models fine-tuned on full training data.

We propose a method for estimation and inference for bounds for heterogeneous causal effect parameters in general sample selection models where the treatment can affect whether an outcome is observed and no exclusion restrictions are available. The method provides conditional effect bounds as functions of policy relevant pre-treatment variables. It allows for conducting valid statistical inference on the unidentified conditional effects. We use a flexible debiased/double machine learning approach that can accommodate non-linear functional forms and high-dimensional confounders. Easily verifiable high-level conditions for estimation, misspecification robust confidence intervals, and uniform confidence bands are provided as well. Re-analyzing data from a large scale field experiment on Facebook, we find significant depolarization effects of counter-attitudinal news subscription nudges. The effect bounds are highly heterogeneous and suggest strong depolarization effects for moderates, conservatives, and younger users.

With the advent of fluent generative language models that can produce convincing utterances very similar to those written by humans, distinguishing whether a piece of text is machine-generated or human-written becomes more challenging and more important, as such models could be used to spread misinformation, fake news, fake reviews and to mimic certain authors and figures. To this end, there have been a slew of methods proposed to detect machine-generated text. Most of these methods need access to the logits of the target model or need the ability to sample from the target. One such black-box detection method relies on the observation that generated text is locally optimal under the likelihood function of the generator, while human-written text is not. We find that overall, smaller and partially-trained models are better universal text detectors: they can more precisely detect text generated from both small and larger models. Interestingly, we find that whether the detector and generator were trained on the same data is not critically important to the detection success. For instance the OPT-125M model has an AUC of 0.81 in detecting ChatGPT generations, whereas a larger model from the GPT family, GPTJ-6B, has AUC of 0.45.

Fox News correspondent Matt Finn has the latest on the impact of AI technology that some say could outpace humans on'Special Report.' Artificial intelligence will take center stage in the nation's capital on Tuesday, when tech CEO Sam Altman testifies for the first time before Congress regarding ChatGPT, his company's revolutionary chatbot. Altman's OpenAI, an AI research lab, revolutionized the technology last year when it released ChatGPT, a chatbot that's able to mimic human conversation based on prompts it is given. The company has gone on to release updated iterations of the chatbot since last November, which has sparked a race in Silicon Valley for other tech companies to build and release more power systems powered by artificial intelligence. Altman will appear before the Senate Judiciary subcommittee on privacy, technology, and the law on Tuesday morning amid pressure on government leaders to craft regulations for artificial intelligence.

Two-time Oscar-winner Tom Hanks could live forever on the big screen with the help of artificial intelligence. Hanks, 66, claims to have predicted the rise of AI in the film industry 20 years ago and believes it will recreate him in films long after he is dead. He said the powers of AI came to him when making the 2004 computer-animated movie The Polar Express when he was reimagined as a digital train conductor. 'What is a bonafide possibility right now is - if I wanted to - I could get together and pitch a series of seven movies that would star me in them in which I would be 32 years old from now until kingdom come,' Hanks said, speaking with British comedian Adam Buxton. 'I can tell you that there's discussions going on in all of the guilds, all of the agencies, and all of the legal firms in order to come up with the legal ramifications of my face and my voice and everybody else's being our intellectual property,' Hanks said.

FIRST ON FOX: While the fast-evolving technology of artificial intelligence may be taking many authors today by surprise, No. 1 New York Times bestselling author Jack Carr is well ahead of the game, as is par for the course for this former Navy SEAL. In a phone interview ahead of the publication of his highly anticipated new novel, "Only the Dead" -- on sale on Tuesday, May 16 -- Carr told Fox News Digital of AI, "In the national security space it will be and probably is being used extensively." He said, "The question now isn't'could we' or'should we,' as AI is already here. The question now is about management of AI across industry. My hope is that AI can be used for the betterment of society -- but as I learned in the SEAL Teams, hope is not a course of action."