We detail the training of the LLM360 K2-65B model, scaling up our 360-degree OPEN SOURCE approach to the largest and most powerful models under project LLM360. While open-source LLMs continue to advance, the answer to "How are the largest LLMs trained?" remains unclear within the community. The implementation details for such high-capacity models are often protected due to business considerations associated with their high cost. This lack of transparency prevents LLM researchers from leveraging valuable insights from prior experience, e.g., "What are the best practices for addressing loss spikes?" The LLM360 K2 project addresses this gap by providing full transparency and access to resources accumulated during the training of LLMs at the largest scale. This report highlights key elements of the K2 project, including our first model, K2 DIAMOND, a 65 billion-parameter LLM that surpasses LLaMA-65B and rivals LLaMA2-70B, while requiring fewer FLOPs and tokens. We detail the implementation steps and present a longitudinal analysis of K2 DIAMOND's capabilities throughout its training process. We also outline ongoing projects such as TXT360, setting the stage for future models in the series. By offering previously unavailable resources, the K2 project also resonates with the 360-degree OPEN SOURCE principles of transparency, reproducibility, and accessibility, which we believe are vital in the era of resource-intensive AI research.

In MMORPGs (Massively Multiplayer Online Role-Playing Games), abnormal players (bots) using unauthorized automated programs to carry out pre-defined behaviors systematically and repeatedly are commonly observed. Bots usually engage in these activities to gain in-game money, which they eventually trade for real money outside the game. Such abusive activities negatively impact the in-game experiences of legitimate users since bots monopolize specific hunting areas and obtain valuable items. Thus, detecting abnormal players is a significant task for game companies. Motivated by the fact that bots tend to behave collectively with similar in-game trajectories due to the auto-programs, we developed BotTRep, a framework that comprises trajectory representation learning followed by clustering using a completely unlabeled in-game trajectory dataset. Our model aims to learn representations for in-game trajectory sequences so that players with contextually similar trajectories have closer embeddings. Then, by applying DBSCAN to these representations and visualizing the corresponding moving patterns, our framework ultimately assists game masters in identifying and banning bots.

As artificial intelligence (AI) systems become increasingly integral to critical infrastructure and global operations, the need for a unified, trustworthy governance framework is more urgent that ever. This paper proposes a novel approach to AI governance, utilizing blockchain and distributed ledger technologies (DLT) to establish a decentralized, globally recognized framework that ensures security, privacy, and trustworthiness of AI systems across borders. The paper presents specific implementation scenarios within the financial sector, outlines a phased deployment timeline over the next decade, and addresses potential challenges with solutions grounded in current research. By synthesizing advancements in blockchain, AI ethics, and cybersecurity, this paper offers a comprehensive roadmap for a decentralized AI governance framework capable of adapting to the complex and evolving landscape of global AI regulation.

The rapid adoption of generative AI in the public sector, encompassing diverse applications ranging from automated public assistance to welfare services and immigration processes, highlights its transformative potential while underscoring the pressing need for thorough risk assessments. Despite its growing presence, evaluations of risks associated with AI-driven systems in the public sector remain insufficiently explored. Building upon an established taxonomy of AI risks derived from diverse government policies and corporate guidelines, we investigate the critical risks posed by generative AI in the public sector while extending the scope to account for its multimodal capabilities. In addition, we propose a Systematic dAta generatIon Framework for evaluating the risks of generative AI (SAIF). SAIF involves four key stages: breaking down risks, designing scenarios, applying jailbreak methods, and exploring prompt types. It ensures the systematic and consistent generation of prompt data, facilitating a comprehensive evaluation while providing a solid foundation for mitigating the risks. Furthermore, SAIF is designed to accommodate emerging jailbreak methods and evolving prompt types, thereby enabling effective responses to unforeseen risk scenarios. We believe that this study can play a crucial role in fostering the safe and responsible integration of generative AI into the public sector.

Modern privacy regulations have spurred the evolution of machine unlearning, a technique enabling a trained model to efficiently forget specific training data. In prior unlearning methods, the concept of "data forgetting" is often interpreted and implemented as achieving zero classification accuracy on such data. Nevertheless, the authentic aim of machine unlearning is to achieve alignment between the unlearned model and the gold model, i.e., encouraging them to have identical classification accuracy. On the other hand, the gold model often exhibits non-zero classification accuracy due to its generalization ability. To achieve aligned data forgetting, we propose a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. Consequently, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data forgetting. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model.

Hate speech and abusive language are global phenomena that need socio-cultural background knowledge to be understood, identified, and moderated. However, in many regions of the Global South, there have been several documented occurrences of (1) absence of moderation and (2) censorship due to the reliance on keyword spotting out of context. Further, high-profile individuals have frequently been at the center of the moderation process, while large and targeted hate speech campaigns against minorities have been overlooked. These limitations are mainly due to the lack of high-quality data in the local languages and the failure to include local communities in the collection, annotation, and moderation processes. To address this issue, we present AfriHate: a multilingual collection of hate speech and abusive language datasets in 15 African languages. Each instance in AfriHate is annotated by native speakers familiar with the local culture. We report the challenges related to the construction of the datasets and present various classification baseline results with and without using LLMs. The datasets, individual annotations, and hate speech and offensive language lexicons are available on https://github.com/AfriHate/AfriHate

The development of neural sequence models, such as Transformers [Vaswani et al., 2017], along with the improvements in large-scale self-supervised learning, has opened the door to universal language understanding and generation. This achievement is largely motivated by pre-training: we separate common components from many neural network-based systems, and then train them on huge amounts of unlabeled data using self-supervision. These pre-trained models serve as foundation models that can be easily adapted to different tasks via fine-tuning or prompting. As a result, the paradigm of NLP has been enormously changed. In many cases, large-scale supervised learning for specific tasks is no longer required, and instead, we only need to adapt pre-trained foundation models.

As Large Language Models (LLMs) and generative AI become increasingly widespread, concerns about content safety have grown in parallel. Currently, there is a clear lack of high-quality, human-annotated datasets that address the full spectrum of LLM-related safety risks and are usable for commercial applications. To bridge this gap, we propose a comprehensive and adaptable taxonomy for categorizing safety risks, structured into 12 top-level hazard categories with an extension to 9 fine-grained subcategories. This taxonomy is designed to meet the diverse requirements of downstream users, offering more granular and flexible tools for managing various risk types. Using a hybrid data generation pipeline that combines human annotations with a multi-LLM "jury" system to assess the safety of responses, we obtain Aegis 2.0, a carefully curated collection of 34,248 samples of human-LLM interactions, annotated according to our proposed taxonomy. To validate its effectiveness, we demonstrate that several lightweight models, trained using parameter-efficient techniques on Aegis 2.0, achieve performance competitive with leading safety models fully fine-tuned on much larger, non-commercial datasets. In addition, we introduce a novel training blend that combines safety with topic following data.This approach enhances the adaptability of guard models, enabling them to generalize to new risk categories defined during inference. We plan to open-source Aegis 2.0 data and models to the research community to aid in the safety guardrailing of LLMs.

This study examines the ethical reasoning of six prominent generative large language models: OpenAI GPT-4o, Meta LLaMA 3.1, Perplexity, Anthropic Claude 3.5 Sonnet, Google Gemini, and Mistral 7B. The research explores how these models articulate and apply ethical logic, particularly in response to moral dilemmas such as the Trolley Problem, and Heinz Dilemma. Departing from traditional alignment studies, the study adopts an explainability-transparency framework, prompting models to explain their ethical reasoning. This approach is analyzed through three established ethical typologies: the consequentialist-deontological analytic, Moral Foundations Theory, and the Kohlberg Stages of Moral Development Model. Findings reveal that LLMs exhibit largely convergent ethical logic, marked by a rationalist, consequentialist emphasis, with decisions often prioritizing harm minimization and fairness. Despite similarities in pre-training and model architecture, a mixture of nuanced and significant differences in ethical reasoning emerge across models, reflecting variations in fine-tuning and post-training processes. The models consistently display erudition, caution, and self-awareness, presenting ethical reasoning akin to a graduate-level discourse in moral philosophy. In striking uniformity these systems all describe their ethical reasoning as more sophisticated than what is characteristic of typical human moral logic.

Fox News' senior national correspondent William La Jeunesse joins'America's Newsroom' to discuss Congress' history of killing pushes for cost-cutting. FIRST ON FOX: The Congressional Department of Government Efficiency (DOGE) Caucus is holding its second-ever meeting on Wednesday, where its leaders are expected to unveil a set of "principles" to guide the group in its mission to cut government waste. They outlined eight goals, some practical while others more symbolic, in a bid to ensure the caucus is in sync with the DOGE advisory panel set up by President-elect Donald Trump. "The federal government must serve the interests of taxpayers, and taxpayers are best served by a lean, efficient, transparent, and accountable bureaucracy," the first principle read, according to a draft memo obtained by Fox News Digital. The document also suggested both lofty and smaller-scale goals.