Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex tasks. Moreover, recent research has shown that incorporating human-annotated rationales (e.g., Chain-of-Thought prompting) during in-context learning can significantly enhance the performance of these models, particularly on tasks that require reasoning capabilities. However, incorporating such rationales poses challenges in terms of scalability as this requires a high degree of human involvement. In this work, we present a novel framework, Amplifying Model Performance by Leveraging In-Context Learning with Post Hoc Explanations (AMPLIFY), which addresses the aforementioned challenges by automating the process of rationale generation. To this end, we leverage post hoc explanation methods which output attribution scores (explanations) capturing the influence of each of the input features on model predictions. More specifically, we construct automated natural language rationales that embed insights from post hoc explanations to provide corrective signals to LLMs. Extensive experimentation with real-world datasets demonstrates that our framework, AMPLIFY, leads to prediction accuracy improvements of about 10-25% over a wide range of tasks, including those where prior approaches which rely on human-annotated rationales such as Chain-of-Thought prompting fall short. Our work makes one of the first attempts at highlighting the potential of post hoc explanations as valuable tools for enhancing the effectiveness of LLMs. Furthermore, we conduct additional empirical analyses and ablation studies to demonstrate the impact of each of the components of AMPLIFY, which, in turn, leads to critical insights for refining in-context learning.

Large Language Models (LLMs) are capable of successfully performing many language processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify and explain social phenomena like persuasiveness and political ideology, then LLMs could augment the Computational Social Science (CSS) pipeline in important ways. This work provides a road map for using LLMs as CSS tools. Towards this end, we contribute a set of prompting best practices and an extensive evaluation pipeline to measure the zero-shot performance of 13 language models on 25 representative English CSS benchmarks. On taxonomic labeling tasks (classification), LLMs fail to outperform the best fine-tuned models but still achieve fair levels of agreement with humans. On free-form coding tasks (generation), LLMs produce explanations that often exceed the quality of crowdworkers' gold references. We conclude that the performance of today's LLMs can augment the CSS research pipeline in two ways: (1) serving as zero-shot data annotators on human annotation teams, and (2) bootstrapping challenging creative generation tasks (e.g., explaining the underlying attributes of a text). In summary, LLMs are posed to meaningfully participate in} social science analysis in partnership with humans.

Generative artificial intelligence has made significant strides, producing text indistinguishable from human prose and remarkably photorealistic images. Automatically measuring how close the generated data distribution is to the target distribution is central to diagnosing existing models and developing better ones. We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images. These scores are statistical summaries of divergence frontiers capturing two types of errors in generative modeling. We explore three approaches to statistically estimate these scores: vector quantization, non-parametric estimation, and classifier-based estimation. We provide statistical bounds for the vector quantization approach. Empirically, we find that the proposed scores paired with a range of $f$-divergences and statistical estimation methods can quantify the gaps between the distributions of human-written text and those of modern neural language models by correlating with human judgments and identifying known properties of the generated texts. We demonstrate in the vision domain that MAUVE can identify known properties of generated images on par with or better than existing metrics. In conclusion, we present practical recommendations for using MAUVE effectively with language and image modalities.

AMD announced the Ryzen 8040 series of laptop processors at the company's AI-themed event, reframing what has been a conversation about CPU speed, power, and battery life into one that prioritizes AI. In January, AMD launched the Ryzen 7000 family, of which the Ryzen 7040 included the first use of what AMD then called its XDNA architecture, powering Ryzen AI. (When rival Intel disclosed its Meteor Lake processor this past summer, Intel began referring to the AI accelerator as an NPU, and the name stuck.) More than 50 laptop models already ship with Ryzen AI, executives said. In AMD's case, the XDNA NPU assists the Zen CPU, with the Radeon RDNA architecture of the GPU powering graphics. But all three logic components work harmoniously, contributing to the greater whole.

Pichai, who previously oversaw Chrome and Android, is famously product obsessed. In his first founder's letter as CEO in 2016, he predicted that "[w]e will move from mobile first to an AI first world." In the years since, Pichai has infused AI deeply into all of Google's products, from Android devices all the way up to the cloud. Despite that, the last year has largely been defined by the AI releases from another company, OpenAI. The rollout of DALL-E and GPT-3.5 last year, followed by GPT-4 this year, dominated the sector and kicked off an arms race between startups and tech giants alike.

What do Taylor Swift, Andrew Tate and Robert Oppenheimer all have in common? They were the most searched articles on Wikipedia this year. The platform shared a fascinating report revealing the topics most interested people in English-speaking countries. Collectively, we racked up more than 84 billion views on Wikipedia this year. The site's page for ChatGPT was the top article, with more than 49 million views, following its breakout year that sparked curiosity and concern worldwide. Curiosity and concern also played a part in the second most viewed Wikipedia article of the year: 'Deaths in 2023' ' which HAD over 42 million views.

Google DeepMind has announced its much-anticipated family of artificial intelligence chatbots, Gemini, which will compete with OpenAI's GPT series. According to Google, Gemini Ultra, its largest and most capable new model, outperforms OpenAI's most capable model, GPT-4, at a number of text-based, image-based, coding, and reasoning tasks. Gemini Ultra will be available through a new AI chat feature called Bard Advanced from early next year, the company said. It is currently being refined and is undergoing "trust and safety checks, including red-teaming by trusted external parties," according to the announcement. Google DeepMind also announced the launch of Gemini Pro, which is now available to the public through Google's Bard chat interface, and the smaller Gemini Nano, which will run on Google's Pixel 8 Pro smartphone.

However, a new, more powerful version of the OpenAI software is due to be released next year, with chief executive Sam Altman saying the firm's new products would make its current ones look like "a quaint relative".

Facebook owner Meta has been an AI player for years, hiring some of the field's smartest researchers and using the tech to help decide which of its users should see certain advertisements. In July, it doubled down on a very different approach to AI than its Big Tech rivals. It announced that Llama 2, its GPT4 competitor, would be "open source" -- available for anyone to download, modify and add to their own products for free. The approach won Meta plaudits from tech start-ups who were worried that Google, Microsoft and OpenAI would try to corner the market for advanced AI and squeeze out any competitors. But it's also been criticized for making it easier for people to use AI for malicious purposes.

OpenAI's spot atop the generative AI heap may be coming to an end as Google officially introduced its most capable large language model to date on Wednesday, dubbed Gemini 1.0. It's the first of "a new generation of AI models, inspired by the way people understand and interact with the world," CEO Sundar Pichai wrote in a Google blog post. "Ever since programming AI for computer games as a teenager, and throughout my years as a neuroscience researcher trying to understand the workings of the brain, I've always believed that if we could build smarter machines, we could harness them to benefit humanity in incredible ways," Pichai continued. The result of extensive collaboration between Google's DeepMind and Research divisions, Gemini has all the bells and whistles cutting-edge genAIs have to offer. "Its capabilities are state-of-the-art in nearly every domain," Pichai declared.