In-context Learning (ICL) has emerged as a powerful capability alongside the development of scaled-up large language models (LLMs). By instructing LLMs using few-shot demonstrative examples, ICL enables them to perform a wide range of tasks without updating millions of parameters. However, the precise contributions of demonstrations towards improving end-task performance have not been thoroughly investigated in recent analytical studies. In this paper, we empirically decompose the overall performance of ICL into three dimensions, label space, format, and discrimination, and we evaluate four general-purpose LLMs across a diverse range of tasks. Counter-intuitively, we find that the demonstrations have a marginal impact on provoking discriminative knowledge of language models. However, ICL exhibits significant efficacy in regulating the label space and format which helps LLMs to respond in desired label words. We then demonstrate this ability functions similar to detailed instructions for LLMs to follow. We additionally provide an in-depth analysis of the mechanism of retrieval helping with ICL and find that retrieving the most semantically similar examples notably boosts model's discriminative capability.

Executing safe and precise flight maneuvers in dynamic high-speed winds is important for the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the relationship between various wind conditions and its effect on aircraft maneuverability is not well understood, it is challenging to design effective robot controllers using traditional control design methods. We present Neural-Fly, a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning. Neural-Fly builds on two key observations that aerodynamics in different wind conditions share a common representation and that the wind-specific part lies in a low-dimensional space. To that end, Neural-Fly uses a proposed learning algorithm, domain adversarially invariant meta-learning (DAIML), to learn the shared representation, only using 12 minutes of flight data. With the learned representation as a basis, Neural-Fly then uses a composite adaptation law to update a set of linear coefficients for mixing the basis elements. When evaluated under challenging wind conditions generated with the Caltech Real Weather Wind Tunnel, with wind speeds up to 43.6 kilometers/hour (12.1 meters/second), Neural-Fly achieves precise flight control with substantially smaller tracking error than state-of-the-art nonlinear and adaptive controllers. In addition to strong empirical performance, the exponential stability of Neural-Fly results in robustness guarantees. Last, our control design extrapolates to unseen wind conditions, is shown to be effective for outdoor flights with only onboard sensors, and can transfer across drones with minimal performance degradation.

Automatic lexical simplification is a task to substitute lexical items that may be unfamiliar and difficult to understand with easier and more common words. This paper presents MultiLS-SP/CA, a novel dataset for lexical simplification in Spanish and Catalan. This dataset represents the first of its kind in Catalan and a substantial addition to the sparse data on automatic lexical simplification which is available for Spanish. Specifically, MultiLS-SP is the first dataset for Spanish which includes scalar ratings of the understanding difficulty of lexical items. In addition, we describe experiments with this dataset, which can serve as a baseline for future work on the same data.

This study examines the effects of de-globalization trends on international trade networks and their role in improving forecasts for economic growth. Using section-level trade data from nearly 200 countries from 2010 to 2022, we identify significant shifts in the network topology driven by rising trade policy uncertainty. Our analysis highlights key global players through centrality rankings, with the United States, China, and Germany maintaining consistent dominance. Using a horse race of supervised regressors, we find that network topology descriptors evaluated from section-specific trade networks substantially enhance the quality of a country's GDP growth forecast. We also find that non-linear models, such as Random Forest, XGBoost, and LightGBM, outperform traditional linear models used in the economics literature. Using SHAP values to interpret these non-linear model's predictions, we find that about half of most important features originate from the network descriptors, underscoring their vital role in refining forecasts. Moreover, this study emphasizes the significance of recent economic performance, population growth, and the primary sector's influence in shaping economic growth predictions, offering novel insights into the intricacies of economic growth forecasting.

Temporal expression (TE) normalization is a well-studied problem. However, the predominately used rule-based systems are highly restricted to specific settings, and upcoming machine learning approaches suffer from a lack of labeled data. In this work, we explore the feasibility of proprietary and open-source large language models (LLMs) for TE normalization using in-context learning to inject task, document, and example information into the model. We explore various sample selection strategies to retrieve the most relevant set of examples. By using a window-based prompt design approach, we can perform TE normalization across sentences, while leveraging the LLM knowledge without training the model. Our experiments show competitive results to models designed for this task. In particular, our method achieves large performance improvements for non-standard settings by dynamically including relevant examples during inference.

Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. In this paper, we develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We first build a dataset, GlobalOpinionQA, comprised of questions and answers from cross-national surveys designed to capture diverse opinions on global issues across different countries. Next, we define a metric that quantifies the similarity between LLM-generated survey responses and human responses, conditioned on country. With our framework, we run three experiments on an LLM trained to be helpful, honest, and harmless with Constitutional AI. By default, LLM responses tend to be more similar to the opinions of certain populations, such as those from the USA, and some European and South American countries, highlighting the potential for biases. When we prompt the model to consider a particular country's perspective, responses shift to be more similar to the opinions of the prompted populations, but can reflect harmful cultural stereotypes. When we translate GlobalOpinionQA questions to a target language, the model's responses do not necessarily become the most similar to the opinions of speakers of those languages. We release our dataset for others to use and build on. Our data is at https://huggingface.co/datasets/Anthropic/llm_global_opinions. We also provide an interactive visualization at https://llmglobalvalues.anthropic.com.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. BRUSSELS (AP) -- European Union lawmakers approved Wednesday a major revamp of the bloc's migration laws, hoping to end years of division over how to manage the entry of thousands of people without authorization and deprive the far right of a vote-winning campaign issue ahead of June elections. In a series of 10 votes, members of the European Parliament endorsed the regulations and policies that make up the Pact on Migration and Asylum. The reforms address the thorny issue of who should take responsibility for migrants when they arrive and whether other EU countries should be obliged to help. The proceedings were briefly interrupted by a small but noisy group of demonstrators in the public gallery who wore shirts marked "this pact kills" and shouted "vote no!" European Commissioner for Home Affairs Ylva Johansson, is embraced after Members of the European Parliament participated in a series of votes during a plenary session at the European Parliament in Brussels, Wednesday, April 10, 2024.

Frank Kendall, the secretary of the Air Force, told the U.S. Senate Committee on Appropriations he will get to fly in an AI-flown plane later this year. Air Force Secretary Frank Kendall told members of the U.S. Senate on Tuesday that he plans to ride in the cockpit of an aircraft operated by artificial intelligence. An F-16 169th Fighter Wing jet is seen in 2023. FLIGHT RISKS: Air Force Secretary Frank Kendall told members of the U.S. Senate on Tuesday that he plans to ride in the cockpit of an aircraft operated by artificial intelligence to experience the technology of the military branch's future fleet. 'KEEPING BEAUTY REAL': As experts predict that 90% of online content could be generated by artificial intelligence by the year 2025, a major beauty brand is taking a stand against the use of AI in advertising.

Recently, Donald Trump fans in Florida and Michigan have been auto-generating and spreading around faked "pictures" of Trump surrounded by crowds of Black supporters--and earning significant traction for doing so. Coming at a time when President Joe Biden is worried about losing the Black voters who came out for his 2020 election, the Trump images have become a whole new subgenre of A.I. sludge. And no one in any position of power appears to know what to do about it. Last month, BBC Panorama reported on the proliferation of these deceitful likenesses. The first example displayed Trump at a Christmas party with his arm around a couple of Black women, one of whom is seen wearing a Pen & Pixel–style tank; another shows him sitting on a house porch with six young Black men, smiling with his hands clasped.

"AI has the disruptive potential of changing our economy, our political system, and our day-to-day lives. We must balance the immense potential of AI with the crucial need for ethical guidelines and protections." said Congressman Schiff in a statement. He added that the bill "champions innovation while safeguarding the rights and contributions of creators, ensuring they are aware when their work contributes to AI training datasets. This is about respecting creativity in the age of AI and marrying technological progress with fairness." Organizations such as the Recording Industry Association of America (RIAA), SAG-AFTRA and WGA have shown support for the bill. They would also have to provide the same information retroactively for any existing tools and make updates if they considerably altered datasets.