The Trump Administration's Data Center Push Could Open the Door for New Forever Chemicals The EPA is prioritizing review of new chemicals to be used in data centers. Experts say this could lead to the fast approval of new types of forever chemicals--with limited oversight. In recent months, the Trump administration has opened a deregulatory floodgate in the name of building more data centers. Among other things, this has involved ordering rollbacks of clean water regulations and opening up public lands to coal mining. Now, it's turning its eye to chemical regulation with a new policy that could, experts say, potentially fast-track the approval of new chemicals for use in the US--including new types of forever chemicals--with limited oversight. In September, the EPA announced it would be prioritizing the regulatory review of new chemicals used in data centers or related projects.

"We learn who is furloughed when we send an email to someone and get the out-of-office message," one employee tells WIRED. Workers at the Environmental Protection Agency tell WIRED that they have faced increasing chaos over the past five weeks. In recent weeks, varied phases of furloughs have forced staff to go home in seemingly random waves. Some employees remaining at the agency are working on policies friendly to fossil fuel and industrial interests that are a priority of the administration, even as the rest of the government shuts down. Others have had to sit on their hands, as the shutdown takes out colleagues with no notice--and remaining employees have little to no information as to what is coming next.

The EPA Is Ending Greenhouse Gas Data Collection. Who Will Step Up to Fill the Gap? With the agency no longer collecting emissions data from polluting companies, attention is turning to whether climate NGOs have the tools--and legal right--to fulfill this EPA function. The Environmental Protection Agency announced earlier this month that it would stop making polluting companies report their greenhouse gas emissions to it, eliminating a crucial tool the US uses to track emissions and form climate policy. Climate NGOs say their work could help plug some of the data gap, but they and other experts fear the EPA's work can't be fully matched. "I don't think this system can be fully replaced," says Joseph Goffman, the former assistant administrator at the EPA's Office of Air and Radiation.

It's Not Going to Get It From Trump's Corporate-Friendly EPA The White House's new Make America Healthy Again strategy makes some asks of the EPA--but critics say the agency is too industry-friendly to make a difference. When Jean-Marie Kauth first read the Make America Healthy Again commission report, released by the White House in May, she was "thrilled about some of the things they identified," she says. "They clearly called out industry as a pernicious influence on why EPA has not been very successful in regulating chemicals, especially pesticides." Kauth's daughter died of leukemia at age 8 after, Kauth says, she was exposed to the insecticide chlorpyrifos, which the EPA banned in 2021. Kauth, a professor at Benedictine University in Illinois, now serves as a member of the EPA's Children's Health Protection Advisory Committee (CHPAC), a group of outside experts who advise the agency on children's health issues.

Targeted data poisoning attacks pose an increasingly serious threat due to their ease of deployment and high success rates. These attacks aim to manipulate the prediction for a single test sample in classification models. Unlike indiscriminate attacks that aim to decrease overall test performance, targeted attacks present a unique threat to individual test instances. This threat model raises a fundamental question: what factors make certain test samples more susceptible to successful poisoning than others? We investigate how attack difficulty varies across different test instances and identify key characteristics that influence vulnerability. This paper introduces three predictive criteria for targeted data poisoning difficulty: ergodic prediction accuracy (analyzed through clean training dynamics), poison distance, and poison budget. Our experimental results demonstrate that these metrics effectively predict the varying difficulty of real-world targeted poisoning attacks across diverse scenarios, offering practitioners valuable insights for vulnerability assessment and understanding data poisoning attacks.

Fox News anchor Bret Baier examines the U.S. power supply on'Special Report.' The global race to harness the power of artificial intelligence (AI) has begun. President Donald Trump got it right from the start when he issued an executive order in January to strengthen America's AI – the next great technological forefront. From Day One as Environmental Protection Agency (EPA) administrator, it was clear that EPA would have a major hand in permitting reform to cut down barriers that have acted as a roadblock so we can bolster the growth of AI and make America the AI capital of the world. In fact, it's an endeavor so important, it is a core pillar of my Powering the Great American Comeback initiative.

President Trump this week continued to make his environmental priorities clear by vowing to open up hundreds of coal power plants in the United States in an effort to advance competition against China. "After years of being held captive by Environmental Extremists, Lunatics, Radicals, and Thugs, allowing other Countries, in particular China, to gain tremendous Economic advantage over us by opening up hundreds of all Coal Fire Power Plants, I am authorizing my Administration to immediately begin producing Energy with BEAUTIFUL, CLEAN COAL," Trump wrote in a post on social media Monday. Though the post was not linked to any particular policy plans or documents, it arrives as the White House takes aim at various environmental agencies and clean-energy initiatives. In the last week alone, the administration has announced plans to significantly roll back regulations that govern coal production and to potentially lay off up to 65% of scientists and researchers at the Environmental Protection Agency, among other actions. Coal accounts for about 16% of the country's electricity generation, according to the U.S. Energy Information Administration -- down from about 50% in 2000 as natural gas and nuclear and renewable energy have grown.

Since the debut of DPO, it has been shown that aligning a target LLM with human preferences via the KL-constrained RLHF loss is mathematically equivalent to a special kind of reward modeling task. Concretely, the task requires: 1) using the target LLM to parameterize the reward model, and 2) tuning the reward model so that it has a 1:1 linear relationship with the true reward. However, we identify a significant issue: the DPO loss might have multiple minimizers, of which only one satisfies the required linearity condition. The problem arises from a well-known issue of the underlying Bradley-Terry preference model: it does not always have a unique maximum likelihood estimator (MLE). Consequently,the minimizer of the RLHF loss might be unattainable because it is merely one among many minimizers of the DPO loss. As a better alternative, we propose an energy-based model (EBM) that always has a unique MLE, inherently satisfying the linearity requirement. To approximate the MLE in practice, we propose a contrastive loss named Energy Preference Alignment (EPA), wherein each positive sample is contrasted against one or more strong negatives as well as many free weak negatives. Theoretical properties of our EBM enable the approximation error of EPA to almost surely vanish when a sufficient number of negatives are used. Empirically, we demonstrate that EPA consistently delivers better performance on open benchmarks compared to DPO, thereby showing the superiority of our EBM.

Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations. However, its accuracy drops significantly in spoken dialogue environments due to named entity errors from Automatic Speech Recognition (ASR) systems. We introduce a simple yet effective data augmentation method that targets those entities to improve the robustness of DST model. Our novel method can control the placement of errors using keyword-highlighted prompts while introducing phonetically similar errors. As a result, our method generated sufficient error patterns on keywords, leading to improved accuracy in noised and low-accuracy ASR environments.

Large language models (LLMs) have shown promising performance on various NLP tasks via task prompting. And their performance can be further improved by appending task demonstrations to the head of the prompt. And usually, a better performance can be achieved with more demonstrations. However, asking the users to write the demonstrations can be cumbersome. As a simple yet cost-effective workaround, this paper proposes a novel method called EPA (\textbf{E}asy \textbf{P}rompt \textbf{A}ugmentation)\footnote{While this paper considers augmenting prompts via demonstrations, we name it EPA as the name EDA is already taken by a well-known NLP method \citep{wei-zou-2019-eda}.} that effectively minimizes user efforts in writing demonstrations while improving the model performance at the same time. EPA achieves these goals by automatically augmenting the demonstrations with multiple sources/targets, where each of them paraphrases each other. This is well motivated as augmenting data via paraphrasing effectively improves neural language models. EPA thus employs paraphrasing as an augmentation method for in-context learning. Extensive experiments indicate that EPA effectively improves both NLU and NLG tasks, covering from natural language inference to machine translation in translating tens of languages.\footnote{Code and data will be released upon publication.}