Large Language Models (LLMs) have shown promise in accelerating the scientific research pipeline. A key capability for this process is the ability to generate novel research ideas, and prior studies have found settings in which LLM-generated research ideas were judged as more novel than human-expert ideas. However, a good idea should not simply appear to be novel, it should also result in better research after being executed. To test whether AI-generated ideas lead to better research outcomes, we conduct an execution study by recruiting 43 expert researchers to execute randomly-assigned ideas, either written by experts or generated by an LLM. Each expert spent over 100 hours implementing the idea and wrote a 4-page short paper to document the experiments. All the executed projects are then reviewed blindly by expert NLP researchers. Comparing the review scores of the same ideas before and after execution, the scores of the LLM-generated ideas decrease significantly more than expert-written ideas on all evaluation metrics (novelty, excitement, effectiveness, and overall; p < 0.05), closing the gap between LLM and human ideas observed at the ideation stage. When comparing the aggregated review scores from the execution study, we even observe that for many metrics there is a flip in rankings where human ideas score higher than LLM ideas. This ideation-execution gap highlights the limitations of current LLMs in generating truly effective research ideas and the challenge of evaluating research ideas in the absence of execution outcomes.

Real-world live retrieval-augmented generation (RAG) systems face significant challenges when processing user queries that are often noisy, ambiguous, and contain multiple intents. While RAG enhances large language models (LLMs) with external knowledge, current systems typically struggle with such complex inputs, as they are often trained or evaluated on cleaner data. This paper introduces Omni-RAG, a novel framework designed to improve the robustness and effectiveness of RAG systems in live, open-domain settings. Omni-RAG employs LLM-assisted query understanding to preprocess user inputs through three key modules: (1) Deep Query Understanding and Decomposition, which utilizes LLMs with tailored prompts to denoise queries (e.g., correcting spelling errors) and decompose multi-intent queries into structured sub-queries; (2) Intent-Aware Knowledge Retrieval, which performs retrieval for each sub-query from a corpus (i.e., FineWeb using OpenSearch) and aggregates the results; and (3) Reranking and Generation, where a reranker (i.e., BGE) refines document selection before a final response is generated by an LLM (i.e., Falcon-10B) using a chain-of-thought prompt. Omni-RAG aims to bridge the gap between current RAG capabilities and the demands of real-world applications, such as those highlighted by the SIGIR 2025 LiveRAG Challenge, by robustly handling complex and noisy queries.

Traditional benchmarks for large language models (LLMs) typically rely on static evaluations through storytelling or opinion expression, which fail to capture the dynamic requirements of real-time information processing in contemporary applications. To address this limitation, we present DynamicBench, a benchmark designed to evaluate the proficiency of LLMs in storing and processing up-to-the-minute data. DynamicBench utilizes a dual-path retrieval pipeline, integrating web searches with local report databases. It necessitates domain-specific knowledge, ensuring accurate responses report generation within specialized fields. By evaluating models in scenarios that either provide or withhold external documents, DynamicBench effectively measures their capability to independently process recent information or leverage contextual enhancements. Additionally, we introduce an advanced report generation system adept at managing dynamic information synthesis. Our experimental results confirm the efficacy of our approach, with our method achieving state-of-the-art performance, surpassing GPT4o in document-free and document-assisted scenarios by 7.0% and 5.8%, respectively. The code and data will be made publicly available.

Arabic dialect recognition presents a significant challenge in speech technology due to the linguistic diversity of Arabic and the scarcity of large annotated datasets, particularly for underrepresented dialects. This research investigates hybrid modeling strategies that integrate classical signal processing techniques with deep learning architectures to address this problem in low-resource scenarios. Two hybrid models were developed and evaluated: (1) Mel-Frequency Cepstral Coefficients (MFCC) combined with a Convolutional Neural Network (CNN), and (2) Discrete Wavelet Transform (DWT) features combined with a Recurrent Neural Network (RNN). The models were trained on a dialect-filtered subset of the Common Voice Arabic dataset, with dialect labels assigned based on speaker metadata. Experimental results demonstrate that the MFCC + CNN architecture achieved superior performance, with an accuracy of 91.2% and strong precision, recall, and F1-scores, significantly outperforming the Wavelet + RNN configuration, which achieved an accuracy of 66.5%. These findings highlight the effectiveness of leveraging spectral features with convolutional models for Arabic dialect recognition, especially when working with limited labeled data. The study also identifies limitations related to dataset size, potential regional overlaps in labeling, and model optimization, providing a roadmap for future research. Recommendations for further improvement include the adoption of larger annotated corpora, integration of self-supervised learning techniques, and exploration of advanced neural architectures such as Transformers. Overall, this research establishes a strong baseline for future developments in Arabic dialect recognition within resource-constrained environments.

Forecasting geopolitical conflict from data sources like the Global Database of Events, Language, and Tone (GDELT) is a critical challenge for national security. The inherent sparsity, burstiness, and overdispersion of such data cause standard deep learning models, including the Temporal Fusion Transformer (TFT), to produce unreliable long-horizon predictions. We introduce STFT-VNNGP, a hybrid architecture that won the 2023 Algorithms for Threat Detection (ATD) competition by overcoming these limitations. Designed to bridge this gap, our model employs a two-stage process: first, a TFT captures complex temporal dynamics to generate multi-quantile forecasts. These quantiles then serve as informed inputs for a Variational Nearest Neighbor Gaussian Process (VNNGP), which performs principled spatiotemporal smoothing and uncertainty quantification. In a case study forecasting conflict dynamics in the Middle East and the U.S., STFT-VNNGP consistently outperforms a standalone TFT, showing a superior ability to predict the timing and magnitude of bursty event periods, particularly at long-range horizons. This work offers a robust framework for generating more reliable and actionable intelligence from challenging event data, with all code and workflows made publicly available to ensure reproducibility.

The rapid progress of Large Language Models (LLMs) has transformed the field of Natural Language Processing (NLP). However, these advancements have primarily concentrated on high-resource languages, leaving many low-resource languages, particularly African languages, largely overlooked. Africa has over 2,000 languages [Ethnologue, 2025], the majority of which face significant challenges such as a lack of data, limited computational resources, insufficient NLP tools, and the absence of standardized benchmarks. This study presents a three-stage review to evaluate LLMs' current status, challenges, and prospects for African languages. The first stage investigates both commercial and open-source LLMs models with more than 7 billion parameters regarding their support for African languages [Wang et al., 2024]. The second stage examines foundational multilingual models that have significantly influenced NLP research and development.

Sen. Tim Kaine, D-Va., tells Fox News Digital he's frustrated by US officials not being forthcoming about the drone incursions over Langley Air Force Base. FIRST ON FOX: A group of House Republicans is demanding details on how government agencies are addressing the growing threat of unauthorized drone incursions on U.S. military installations. In letters sent Thursday, the Subcommittee on Military and Foreign Affairs requested a trove of documents and communications from the Departments of Defense (DoD), Transportation (DOT), and Justice (DOJ). The letters note that in 2024 alone, there were 350 drone incursions at over 100 U.S. military bases. Lawmakers believe many of the responses to the illegal incursions, including an instance where a group of drones traipsed over Langley Air Force Base for over two weeks in December 2023, have been insufficient and fragmented.

As the demand for on-device Large Language Model (LLM) inference grows, energy efficiency has become a major concern, especially for battery-limited mobile devices. Our analysis shows that the memory-bound LLM decode phase dominates energy use, and yet most existing works focus on accelerating the prefill phase, neglecting energy concerns. We introduce Adaptive Energy-Centric Core Selection (AECS) and integrate it into MNN to create the energy-efficient version, MNN-AECS, the first engine-level system solution without requiring root access or OS modifications for energy-efficient LLM decoding. MNN-AECS is designed to reduce LLM decoding energy while keeping decode speed within an acceptable slowdown threshold by dynamically selecting low-power CPU cores. MNN-AECS is evaluated across 5 Android and 2 iOS devices on 5 popular LLMs of various sizes. Compared to original MNN, MNN-AECS cuts down energy use by 23% without slowdown averaged over all 7 devices and 4 datasets. Against other engines, including llama.cpp, executorch, mllm, and MediaPipe, MNN-AECS delivers 39% to 78% energy saving and 12% to 363% speedup on average.

Phenotyping is the process of distinguishing groups of patients to identify different types of disease progression. A recent trend employs low-rank matrix and tensor factorization methods for their capability of dealing with multi-modal, heterogeneous, and missing data. Symptom quantification is crucial for understanding patient experiences in inflammatory bowel disease, especially in conditions such as ulcerative colitis (UC). However, patient-reported symptoms are typically noisy, subjective, and significantly more sparse than other data types. For this reason, they are usually not included in phenotyping and other machine learning methods. This paper explores the application of computational phenotyping to leverage Patient-Reported Outcomes (PROs) using a novel supervised coupled matrix-tensor factorization (SCMTF) method, which integrates temporal PROs and temporal labs with static features to predict medication persistence in ulcerative colitis. This is the first tensor-based method that is both supervised and coupled, it is the first application to the UC domain, and the first application to PROs. We use a deep learning framework that makes the model flexible and easy to train. The proposed method allows us to handle the large amount of missing data in the PROs. The best model predicts changes in medication 8 and 20 months in the future with AUCs of 0.853 and 0.803 on the test set respectively. We derive interpretable phenotypes consisting of static features and temporal features (including their temporal patterns). We show that low-rank matrix and tensor based phenotyping can be successfully applied to the UC domain and to highly missing PRO data. We identify phenotypes useful to predict medication persistence - these phenotypes include several symptom variables, showing that PROs contain relevant infromation that is usually discarded.

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This motivated reasoning at a collective level can be detrimental to society when debating critical issues such as human-driven climate change or vaccine safety, and can further aggravate political polarization. Prior studies have reported that large language models (LLMs) are also susceptible to human-like cognitive biases, however, the extent to which LLMs selectively reason toward identity-congruent conclusions remains largely unexplored. Here, we investigate whether assigning 8 personas across 4 political and socio-demographic attributes induces motivated reasoning in LLMs. Testing 8 LLMs (open source and proprietary) across two reasoning tasks from human-subject studies -- veracity discernment of misinformation headlines and evaluation of numeric scientific evidence -- we find that persona-assigned LLMs have up to 9% reduced veracity discernment relative to models without personas. Political personas specifically, are up to 90% more likely to correctly evaluate scientific evidence on gun control when the ground truth is congruent with their induced political identity. Prompt-based debiasing methods are largely ineffective at mitigating these effects. Taken together, our empirical findings are the first to suggest that persona-assigned LLMs exhibit human-like motivated reasoning that is hard to mitigate through conventional debiasing prompts -- raising concerns of exacerbating identity-congruent reasoning in both LLMs and humans.