Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3, their performances still significantly underperform fine-tuned models in the task of text classification. This is due to (1) the lack of reasoning ability in addressing complex linguistic phenomena (e.g., intensification, contrast, irony etc); (2) limited number of tokens allowed in in-context learning. In this paper, we introduce Clue And Reasoning Prompting (CARP). CARP adopts a progressive reasoning strategy tailored to addressing the complex linguistic phenomena involved in text classification: CARP first prompts LLMs to find superficial clues (e.g., keywords, tones, semantic relations, references, etc), based on which a diagnostic reasoning process is induced for final decisions. To further address the limited-token issue, CARP uses a fine-tuned model on the supervised dataset for $k$NN demonstration search in the in-context learning, allowing the model to take the advantage of both LLM's generalization ability and the task-specific evidence provided by the full labeled dataset. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks, 97.39 (+1.24) on SST-2, 96.40 (+0.72) on AGNews, 98.78 (+0.25) on R8 and 96.95 (+0.6) on R52, and a performance comparable to SOTA on MR (92.39 v.s. 93.3). More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups. Specifically, using 16 examples per class, CARP achieves comparable performances to supervised models with 1,024 examples per class.

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series and is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes. These extensive annotations may empower LLMs to unlock character-driven dialogue capabilities. Furthermore, it can serve as a universal benchmark for evaluating how well can a LLM aligning with a specific character. We benchmark LLMs on HPD using both fine-tuning and in-context learning settings. Evaluation results reveal that although there is substantial room for improvement in generating high-quality, character-aligned responses, the proposed dataset is valuable in guiding models toward responses that better align with the character of Harry Potter.

CyberGuy explains how to use Name Drop to share your contact information with other iPhone users. Imagine scrolling through social media only to stumble upon a version of yourself promoting some random brand, or maybe starring in a commercial you've never seen, or perhaps even endorsing a political stance you've never taken. This eerie scenario isn't far off for Tom Hanks, who recently found his AI-generated twin making a pitch for a dental plan. With an uncanny resemblance to Hanks, this digital doppelganger was seen zealously promoting a dental plan that promises a smile as captivating as the actor's. The AI-generated Hanks seemed to have taken on the role of a dental specialist, making promises of pristine pearly whites.

We're just a couple days away from Amazon's October Prime Day sale, which kicks off on Tuesday and goes through Wednesday. Prime Big Deal Days is the company's second site-wide sale of 2023 and there are already plenty of early deals to be found. You'll need a Prime membership for some, but other discounts are open to everyone. We'll be rounding up the best of what's out there on October 10 and 11, but in the meantime, you can get a jump on a few sales that are already live. This week's best tech deals include lots of Amazon devices like Echo speakers, Echo Show smart displays, Blink cameras, Ring doorbells and the Kindle Kids ereader. Apple's AirPods Pro now come with USB-C charging. They're still the "best for iOS" pick in our wireless earbuds buying guide, as they provide pleasing audio quality, strong active noise cancellation (ANC) and a range of iPhone-friendly features.

In this effort, we consider the impact of regularization on the diversity of actions taken by policies generated from reinforcement learning agents trained using a policy gradient. Policy gradient agents are prone to entropy collapse, which means certain actions are seldomly, if ever, selected. We augment the optimization objective function for the policy with terms constructed from various $\varphi$-divergences and Maximum Mean Discrepancy which encourages current policies to follow different state visitation and/or action choice distribution than previously computed policies. We provide numerical experiments using MNIST, CIFAR10, and Spotify datasets. The results demonstrate the advantage of diversity-promoting policy regularization and that its use on gradient-based approaches have significantly improved performance on a variety of personalization tasks. Furthermore, numerical evidence is given to show that policy regularization increases performance without losing accuracy.

In recent years, there has been a rapid proliferation of AI-generated text, primarily driven by the release of powerful pre-trained language models (PLMs). To address the issue of misuse associated with AI-generated text, various high-performing detectors have been developed, including the OpenAI detector and the Stanford DetectGPT. In our study, we ask how reliable these detectors are. We answer the question by designing a novel approach that can prompt any PLM to generate text that evades these high-performing detectors. The proposed approach suggests a universal evasive prompt, a novel type of soft prompt, which guides PLMs in producing "human-like" text that can mislead the detectors. The novel universal evasive prompt is achieved in two steps: First, we create an evasive soft prompt tailored to a specific PLM through prompt tuning; and then, we leverage the transferability of soft prompts to transfer the learned evasive soft prompt from one PLM to another. Employing multiple PLMs in various writing tasks, we conduct extensive experiments to evaluate the efficacy of the evasive soft prompts in their evasion of state-of-the-art detectors.

The rampant spread of fake news has adversely affected society, resulting in extensive research on curbing its spread. As a notable milestone in large language models (LLMs), ChatGPT has gained significant attention due to its exceptional natural language processing capabilities. In this study, we present a thorough exploration of ChatGPT's proficiency in generating, explaining, and detecting fake news as follows. Generation -- We employ four prompt methods to generate fake news samples and prove the high quality of these samples through both self-assessment and human evaluation. Explanation -- We obtain nine features to characterize fake news based on ChatGPT's explanations and analyze the distribution of these factors across multiple public datasets. Detection -- We examine ChatGPT's capacity to identify fake news. We explore its detection consistency and then propose a reason-aware prompt method to improve its performance. Although our experiments demonstrate that ChatGPT shows commendable performance in detecting fake news, there is still room for its improvement. Consequently, we further probe into the potential extra information that could bolster its effectiveness in detecting fake news.

There is limited information on how voice assistants may spread misinformation, yet some researchers argue they could be particularly effective vectors for falsehoods. Users have "higher trust" in the assistants due to their humanlike characteristics, according to a paper written by researchers at King's College London. Customers may also think the information they're getting is coming directly from the tech companies, rather than a third-party provider, making it seem more reliable, according to the paper.

The demo explains how AI is used in the app and its features. Cross-border data flow will play a vital role in shaping the international artificial intelligence landscape, but fear of balkanized technology shouldn't blind Western countries to China's long-standing ambitions and approach, experts argued. "No one wants a balkanized world, and China doesn't, either," Nate Picarsic, senior fellows focusing on China policy at the Foundation for Defense of Democracies (FDD), told Fox News Digital. "But we shouldn't be leaving them in the driver's seat and defining the terms of all of these new realms just in defense of the global system." "We have to be clear eyed about what they're trying to do, defend our interests, have teeth and guardrails to make sure that they're playing by the rules… otherwise, we end up in an AI and data environment that is defined by Chinese norms and standards, because that's what their ambition is," he added.

Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information and can further improve optical flow. Accordingly, we design a first network that estimates flow and disparity jointly and is trained without supervision. A second network, trained with optical flow from the first as pseudo-labels, takes disparities from the first network, estimates 3D rigid motion at every pixel, and reconstructs optical flow again. A final stage fuses the outputs from the two networks. In contrast with previous methods that only consider camera motion, our method also estimates the rigid motions of dynamic objects, which are of key interest in applications. This leads to better optical flow with visibly more detailed occlusions and object boundaries as a result. Our unsupervised pipeline achieves 7.36% optical flow error on the KITTI-2015 benchmark and outperforms the previous state-of-the-art 9.38% by a wide margin. It also achieves slightly better or comparable stereo depth results. Code will be made available.