We study how in-context learning (ICL) in language models is affected by semantic priors versus input-label mappings. We investigate two setups-ICL with flipped labels and ICL with semantically-unrelated labels-across various model families (GPT-3, InstructGPT, Codex, PaLM, and Flan-PaLM). First, experiments on ICL with flipped labels show that overriding semantic priors is an emergent ability of model scale. While small language models ignore flipped labels presented in-context and thus rely primarily on semantic priors from pretraining, large models can override semantic priors when presented with in-context exemplars that contradict priors, despite the stronger semantic priors that larger models may hold. We next study semantically-unrelated label ICL (SUL-ICL), in which labels are semantically unrelated to their inputs (e.g., foo/bar instead of negative/positive), thereby forcing language models to learn the input-label mappings shown in in-context exemplars in order to perform the task. The ability to do SUL-ICL also emerges primarily with scale, and large-enough language models can even perform linear classification in a SUL-ICL setting. Finally, we evaluate instruction-tuned models and find that instruction tuning strengthens both the use of semantic priors and the capacity to learn input-label mappings, but more of the former.

There has been an increased focus on creating conversational open-domain dialogue systems in the spoken dialogue community. Unlike traditional dialogue systems, these conversational systems cannot assume any specific information need or domain restrictions, i.e., the only inherent goal is to converse with the user on an unknown set of topics. While massive improvements in Natural Language Understanding (NLU) and the growth of available knowledge resources can partially support a robust conversation, these conversations generally lack the rapport between two humans that know each other. We developed a robust open-domain conversational system, Athena, that real Amazon Echo users access and evaluate at scale in the context of the Alexa Prize competition. We experiment with methods intended to increase intimacy between Athena and the user by heuristically developing a rule-based user model that personalizes both the current and subsequent conversations and evaluating specific personal opinion question strategies in A/B studies. Our results show a statistically significant positive impact on perceived conversation quality and length when employing these strategies.

Microsoft has a problem with its new AI-powered Bing Chat: It can get weird, unhinged, and racy. But so can Bing Search -- and Microsoft already solved that problem years ago, with SafeSearch. So why can't it be applied to AI chatbots? The creative elements of Bing Chat and other chatbots are clearly one of their more intriguing features, despite sometimes getting weird. Forget the Turing test, they say: all it matters is if it's interesting. I spent a few hours debating users online following my report that Bing offered up racist slurs when I tried to thread the needle by asking it for ethnic nicknames, a query that -- and this is important -- it had previously declined to answer, or answered generically, using the same prompt.

If you want to convert blog article to video, then this blog is for you. In this article you will learn about two websites that you can use to create video with text, and add voice-over to video. However, with so many options available, choosing the right software for artificial intelligence video creation can be overwhelming. Fliki allows users to transform text-based content into videos with professional-grade voiceovers. One of Fliki's key strengths is its user-friendly interface, making it accessible to non-professionals looking to create high-quality video content.

The MFA Photography, Video & Related Media Department will host a comprehensive, one-day symposium focused on the pervasive emergence of AI & its effects upon the lens & screen arts. This event is the first part of a series of lectures & discussions with artists, theorists, educators, & industry professionals reflecting on the recent explosion of interest, use, & questions surrounding AI image synthesis through tools such as DALL-E, MidJourney, Stable Diffusion, & others. As Charles Traub notes, Once again, a major technological revolution has come upon us. AI has clearly emerged as a now ubiquitous tool. Its impact on the lens & screen arts, & all of our social, intellectual, & scientific practices, is only beginning to be understood.

Libraries are increasingly relying on computational methods, including methods from Artificial Intelligence (AI). This increasing usage raises concerns about the risks of AI that are currently broadly discussed in scientific literature, the media and law-making. In this article we investigate the risks surrounding bias and unfairness in AI usage in classification and automated text analysis within the context of library applications. We describe examples that show how the library community has been aware of such risks for a long time, and how it has developed and deployed countermeasures. We take a closer look at the notion of '(un)fairness' in relation to the notion of 'diversity', and we investigate a formalisation of diversity that models both inclusion and distribution. We argue that many of the unfairness problems of automated content analysis can also be regarded through the lens of diversity and the countermeasures taken to enhance diversity.

Recent advancements in pre-trained language models have enabled convenient methods for generating human-like text at a large scale. Though these generation capabilities hold great potential for breakthrough applications, it can also be a tool for an adversary to generate misinformation. In particular, social media platforms like Twitter are highly susceptible to AI-generated misinformation. A potential threat scenario is when an adversary hijacks a credible user account and incorporates a natural language generator to generate misinformation. Such threats necessitate automated detectors for AI-generated tweets in a given user's Twitter timeline. However, tweets are inherently short, thus making it difficult for current state-of-the-art pre-trained language model-based detectors to accurately detect at what point the AI starts to generate tweets in a given Twitter timeline. In this paper, we present a novel algorithm using stylometric signals to aid detecting AI-generated tweets. We propose models corresponding to quantifying stylistic changes in human and AI tweets in two related tasks: Task 1 - discriminate between human and AI-generated tweets, and Task 2 - detect if and when an AI starts to generate tweets in a given Twitter timeline. Our extensive experiments demonstrate that the stylometric features are effective in augmenting the state-of-the-art AI-generated text detectors.

A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i.e., the 5 Ws; Who, What, Where, When and Why regarding the event) and how people reacted to it (i.e., reported statements). However, existing work on news summarization almost exclusively focuses on the event details. In this work, we propose the novel task of summarizing the reactions of different speakers, as expressed by their reported statements, to a given event. To this end, we create a new multi-document summarization benchmark, SUMREN, comprising 745 summaries of reported statements from various public figures obtained from 633 news articles discussing 132 events. We propose an automatic silver training data generation approach for our task, which helps smaller models like BART achieve GPT-3 level performance on this task. Finally, we introduce a pipeline-based framework for summarizing reported speech, which we empirically show to generate summaries that are more abstractive and factual than baseline query-focused summarization approaches.

We propose GANStrument, a generative adversarial model for instrument sound synthesis. Given a one-shot sound as input, it is able to generate pitched instrument sounds that reflect the timbre of the input within an interactive time. By exploiting instance conditioning, GANStrument achieves better fidelity and diversity of synthesized sounds and generalization ability to various inputs. In addition, we introduce an adversarial training scheme for a pitch-invariant feature extractor that significantly improves the pitch accuracy and timbre consistency. Experimental results show that GANStrument outperforms strong baselines that do not use instance conditioning in terms of generation quality and input editability. Qualitative examples are available online.

This paper presents a multi-agent reinforcement learning (MARL) scheme for proactive Multi-Camera Collaboration in 3D Human Pose Estimation in dynamic human crowds. Traditional fixed-viewpoint multi-camera solutions for human motion capture (MoCap) are limited in capture space and susceptible to dynamic occlusions. Active camera approaches proactively control camera poses to find optimal viewpoints for 3D reconstruction. However, current methods still face challenges with credit assignment and environment dynamics. To address these issues, our proposed method introduces a novel Collaborative Triangulation Contribution Reward (CTCR) that improves convergence and alleviates multi-agent credit assignment issues resulting from using 3D reconstruction accuracy as the shared reward. Additionally, we jointly train our model with multiple world dynamics learning tasks to better capture environment dynamics and encourage anticipatory behaviors for occlusion avoidance. We evaluate our proposed method in four photo-realistic UE4 environments to ensure validity and generalizability. Empirical results show that our method outperforms fixed and active baselines in various scenarios with different numbers of cameras and humans. Figure 1: Left: Two critical challenges in fixed camera approaches. Right: Three active cameras collaborate to best reconstruct the 3D pose of the target (marked in). Marker-less motion capture (MoCap) has broad applications in many areas such as cinematography, medical research, virtual reality (VR), sports, and etc. Their successes can be partly attributed to recent developments in 3D Human pose estimation (HPE) techniques (Tu et al., 2020; Iskakov et al., 2019; Jafarian et al., 2019; Pavlakos et al., 2017b; Lin & Lee, 2021b). A straightforward implementation to solve multi-views 3D HPE is to use fixed cameras. Although being a convenient solution, it is less effective against dynamic occlusions. Moreover, fixed camera solutions confine tracking targets within a constrained space, therefore less applicable to outdoor MoCap. On the contrary, active cameras (Luo et al., 2018; 2019; Zhong et al., 2018a; 2019) such as ones mounted on drones can maneuver proactively against incoming occlusions. Owing to its remarkable flexibility, the active approach has thus attracted overwhelming interest (Tallamraju et al., 2020; Ho et al., 2021; Xu et al., 2017; Kiciroglu et al., 2019; Saini et al., 2022; Cheng et al., 2018; Zhang et al., 2021).