Large language models (LLMs) often need to incorporate external knowledge to solve theme-specific problems. Retrieval-augmented generation (RAG) has shown its high promise, empowering LLMs to generate more qualified responses with retrieved external data and knowledge. However, most RAG methods retrieve relevant documents based on either sparse or dense retrieval methods or their combinations, which overlooks the essential, multi-dimensional, and structured semantic information present in documents. This structured information plays a critical role in finding concise yet highly relevant information for domain knowledge-intensive tasks, such as scientific question-answering (QA). In this work, we introduce a multi-dimensional (cube) structure, Hypercube, which can index and allocate documents in a pre-defined multi-dimensional space. Built on the hypercube, we further propose Hypercube-RAG, a novel RAG framework for precise and efficient retrieval. Given a query, Hypercube-RAG first decomposes it based on its entities, phrases, and topics along with pre-defined hypercube dimensions, and then retrieves relevant documents from cubes by aligning these decomposed components with corresponding dimensions. Experiments on three datasets across different domains demonstrate that our method improves response accuracy by 3.7% and retrieval accuracy by 5.3% over the strongest RAG baseline. It also boosts retrieval efficiency (speed) by one or two magnitudes faster than graph-based RAG. Notably, our Hypercube-RAG inherently offers explainability by revealing those underlying dimensions used for retrieval. The code and data are available at https://github.com/JimengShi/Hypercube-RAG.

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual pre-training, where models are updated with new data rather than retraining from scratch. However, the introduction of new data often causes distribution shifts, leading to performance degradation on previously learned tasks. In this paper, we take a deeper look at two popular proposals for addressing this distribution shift within the continual learning literature: experience replay and gradient alignment. We consider continual pre-training of models within the Llama family of architectures at a large scale across languages with 100 billion tokens of training data in each language, finding that both replay and gradient alignment lead to more stable learning without forgetting. This conclusion holds both as we vary the model scale and as we vary the number and diversity of tasks. Moreover, we are the first to demonstrate the effectiveness of gradient alignment techniques in the context of LLM pre-training and propose an efficient implementation of meta-experience replay (MER) (Riemer et al., 2019a) that imbues experience replay with the benefits of gradient alignment despite negligible compute and memory overhead. Our scaling analysis across model sizes and replay rates indicates that small rates of replaying old examples are definitely a more valuable use of compute than investing in model size, but that it is more compute efficient to scale the size of the model than invest in high rates of replaying old examples. Large Language Models (LLMs) need regular updates to be current with new information and domains, posing a problem for organizations looking to maintain LLMs without repeatedly performing expensive retraining from scratch. Performing updates to a model that has already received pre-training on a new distribution is the classic problem of continual learning (Ring, 1994) or lifelong learning (Thrun, 1994). We should draw a strong distinction between this setting and other settings such as fine-tuning or instruction tuning, which are generally characterized by training on much smaller datasets for a much smaller number of gradient steps.

Large language models (LLMs) have revolutionized natural language processing, yet their propensity for hallucination, generating plausible but factually incorrect or fabricated content, remains a critical challenge. This report provides a comprehensive taxonomy of LLM hallucinations, beginning with a formal definition and a theoretical framework that posits its inherent inevitability in computable LLMs, irrespective of architecture or training. It explores core distinctions, differentiating between intrinsic (contradicting input context) and extrinsic (inconsistent with training data or reality), as well as factuality (absolute correctness) and faithfulness (adherence to input). The report then details specific manifestations, including factual errors, contextual and logical inconsistencies, temporal disorientation, ethical violations, and task-specific hallucinations across domains like code generation and multimodal applications. It analyzes the underlying causes, categorizing them into data-related issues, model-related factors, and prompt-related influences. Furthermore, the report examines cognitive and human factors influencing hallucination perception, surveys evaluation benchmarks and metrics for detection, and outlines architectural and systemic mitigation strategies. Finally, it introduces web-based resources for monitoring LLM releases and performance. This report underscores the complex, multifaceted nature of LLM hallucinations and emphasizes that, given their theoretical inevitability, future efforts must focus on robust detection, mitigation, and continuous human oversight for responsible and reliable deployment in critical applications.

Jim Acosta and James Carville speculated whether President Trump will try to rig the 2026 midterms in his favor on "The Jim Acosta Show." Liberal journalist Jim Acosta "interviewed" the artificially animated avatar of deceased teenager Joaquin Oliver to promote a gun control message on Monday. Working with the gun control group Change the Ref, founded by Oliver's parents, Acosta had conversation on his Substack with an avatar created by the father of the son, who was killed in the Parkland high school shooting in 2018. He would have turned 25 on Monday. "I would like to know what your solution would be for gun violence," Acosta asked.

NVIDIA CEO and co-founder Jensen Huang commends President Donald Trump's A.I. agenda and outlines what the country's job future will look like on'Special Report.' Brilliant Labs has just raised the bar for wearable technology. Their new product, Halo, is the world's thinnest open-source AI glasses, yet it packs more intelligence and capability than any other smartglasses that have come before it. Designed to look and feel like a normal pair of glasses, Halo reimagines what's possible when cutting-edge AI meets sleek design. Unlike bulky smartglasses from other brands, Halo feels natural on your face, weighing just over 40 grams.

How many atoms are there in the observable universe? Current estimates point to a number we would write as 1 followed by 80 zeroes, or 1080. If you peered inside each of these atoms and counted their subatomic particles, you could count a bit higher. But what happens beyond that? Take 1090 – even if you counted every atom and subatomic particle in the known universe, you wouldn't reach this number. In some sense, 1090 has no relation to physical reality.

Vice President JD Vance tore into Europe's censorship policies in a speech at the Munich Security Conference. The Trump administration has been on a monthslong campaign railing against what it says are draconian censorship regulations in Europe that have not only stifled free speech, but have also served as another roadblock amid the artificial intelligence evolution. "In Europe, thousands are being convicted for the crime of criticizing their own governments," the State Department recently posted to X, accompanied by a graphic slamming Europe's Digital Services Act (DSA). The EU adopted the DSA in 2022 to regulate online platforms such as social networks, content-sharing platforms and app stores, and is intended to "prevent illegal and harmful activities online and the spread of disinformation." The law has since faced opposition from the Trump administration amid its free speech promotion on the global stage.

The problem of plastic waste hides in plain sight, a ubiquitous part of our lives we rarely question. But a closer examination of the situation is shocking. To date, humans have created around 11 billion metric tons of plastic, the vast majority of which ends up in landfills or the environment. Only 9% of the plastic ever produced has been recycled. To make matters worse, plastic production is growing dramatically; in fact, half of all plastics in existence have been produced in just the last two decades.

A searchable database of public records concerning use of force and misconduct by California law enforcement officers -- some 1.5 million pages from nearly 700 law enforcement agencies -- is now available to the public. The Police Records Access Project, a database built by UC Berkeley and Stanford University, is being published by the Los Angeles Times, San Francisco Chronicle, KQED and CalMatters. It will vastly expand public access to internal affairs records that show how law enforcement agencies throughout the state handle misconduct allegations and uses of police force that result in death or serious injury. The database currently includes records from nearly 12,000 cases. The database is the product of years of work by a multidisciplinary team of journalists, data scientists, lawyers and civil liberties advocates, led by the Berkeley Institute for Data Science (BIDS), UC Berkeley Journalism's Investigative Reporting Program (IRP) and Stanford University's Big Local News.

How long does it take to identify the helmet of a hiker lost in a 183-hectare mountain area, analyzing 2,600 frames taken by a drone from approximately 50 meters away? If done with a human eye, weeks or months. If analyzed by an artificial intelligence system, one afternoon. The National Alpine and Speleological Rescue Corps, known by it's Italian initialism CNSAS, relied on AI to find the body of a person missing in Italy's Piedmont region on the north face of Monviso--the highest peak in the Cottian Alps--since September 2024. According to Saverio Isola, the CNSAS drone pilot who intervened along with his colleague Giorgio Viana, the operation--including searching for any sign of the missing hiker, the discovery and recovery of his body, and a stoppage due to bad weather--lasted less than three days.