In this study, we evaluate open-source models for security incident classification, comparing them with proprietary models. We utilize a dataset of anonymized real incidents, categorized according to the NIST SP 800-61r3 taxonomy and processed using five prompt-engineering techniques (PHP, SHP, HTP, PRP, and ZSL). The results indicate that, although proprietary models still exhibit higher accuracy, locally deployed open-source models provide advantages in privacy, cost-effectiveness, and data sovereignty. According to CERT.br, Brazil reported over 516k security incidents in 2024 and more than 181k in the first half of 2025, underscoring a persistent upward trend that challenges SOCs and CSIRTs to manage high alert volumes efficiently [1]. To alleviate this overload, AI-driven solutions, particularly prompt-engineering techniques such as Progressive Hint Prompting (PHP), have demonstrated over 90% accuracy with models like GPT -4o and Gemini 2 [2].

Spontaneous speech presents several challenges for speech synthesis, particularly in capturing the natural flow of conversation, including turn-taking, pauses, and disfluencies. Although speech synthesis systems have made significant progress in generating natural and intelligible speech, primarily through architectures that implicitly model prosodic features such as pitch, intensity, and duration, the construction of datasets with explicit prosodic segmentation and their impact on spontaneous speech synthesis remains largely unexplored. This paper evaluates the effects of manual and automatic prosodic segmentation annotations in Brazilian Portuguese on the quality of speech synthesized by a non-autoregressive model, FastSpeech 2. Experimental results show that training with prosodic segmentation produced slightly more intelligible and acoustically natural speech. While automatic segmentation tends to create more regular segments, manual prosodic segmentation introduces greater variability, which contributes to more natural prosody. Analysis of neutral declarative utterances showed that both training approaches reproduced the expected nuclear accent pattern, but the prosodic model aligned more closely with natural pre-nuclear contours. To support reproducibility and future research, all datasets, source codes, and trained models are publicly available under the CC BY-NC-ND 4.0 license.

Today's large language models (LLMs) are capable of supporting multilingual scenarios, allowing users to interact with LLMs in their native languages. When LLMs respond to subjective questions posed by users, they are expected to align with the views of specific demographic groups or historical periods, shaped by the language in which the user interacts with the model. Existing studies mainly focus on researching the opinions represented by LLMs among demographic groups in the United States or a few countries, lacking worldwide country samples and studies on human opinions in different historical periods, as well as lacking discussion on using language to steer LLMs. Moreover, they also overlook the potential influence of prompt language on the alignment of LLMs' opinions. In this study, our goal is to fill these gaps. To this end, we create an evaluation framework based on the World Values Survey (WVS) to systematically assess the alignment of LLMs with human opinions across different countries, languages, and historical periods around the world. We find that LLMs appropriately or over-align the opinions with only a few countries while under-aligning the opinions with most countries. Furthermore, changing the language of the prompt to match the language used in the questionnaire can effectively steer LLMs to align with the opinions of the corresponding country more effectively than existing steering methods. At the same time, LLMs are more aligned with the opinions of the contemporary population. To our knowledge, our study is the first comprehensive investigation of the topic of opinion alignment in LLMs across global, language, and temporal dimensions. Our code and data are publicly available at https://github.com/ku-nlp/global-opinion-alignment and https://github.com/nlply/global-opinion-alignment.

In this episode of Uncanny Valley, we discuss our scoop about how the Department of Homeland Security illegally collected Chicago residents' data for month, as well as the news of the week. In today's episode, host Zoë Schiffer is joined by executive editor Brian Barrett to discuss five stories you need to know about this week--from how AI affairs can now be grounds for divorce, to why Google is suing one of the largest networks of text scammers. Then, we dive into how the Department of Homeland Security illegally gathered the data of hundreds of Chicago residents. If the US Has to Build Data Centers, Here's Where They Should Go This Is the Platform Google Claims Is Behind a'Staggering' Scam Text Operation AI Relationships Are on the Rise. Please help us improve Uncanny Valley by filling out our listener survey. Write to us at uncannyvalley@wired.com. You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link. Note: This is an automated transcript, which may contain errors. Today on the show, we're bringing you five stories that you need to know about this week, including our scoop about how the Department of Homeland Security, or DHS, collected Chicago residents' data for months in violation of domestic espionage rules. I'm joined today by WIRED's executive editor Brian Barrett.

Fulkerson's algorithm, we develop a polynomial-time algorithm for computing the

Senior Pentagon officials have arrived in Ukraine to discuss efforts to end the war with Russia, the US military has said. The team, led by US Army Secretary Dan Driscoll, is expected to meet Ukrainian President Volodymyr Zelensky in Kyiv on Thursday when he returns from a trip to Turkey. Reports began surfacing on Wednesday that the US and Russia had prepared a new peace plan, containing major concessions from Ukraine. Neither Washington nor Moscow has officially confirmed the plan. Earlier in the day, at least 26 people were killed in a Russian missile and drone attack on Ukraine's western city of Ternopil, officials there said.

To benchmark a model's long-form factuality in open domains, we first use GPT -4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE).