In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questions about how red teaming operations should be conducted. Based on our experience red teaming over 100 generative AI products at Microsoft, we present our internal threat model ontology and eight main lessons we have learned: 1. Understand what the system can do and where it is applied 2. You don't have to compute gradients to break an AI system 3. AI red teaming is not safety benchmarking 4. Automation can help cover more of the risk landscape 5. The human element of AI red teaming is crucial 6. Responsible AI harms are pervasive but difficult to measure 7. LLMs amplify existing security risks and introduce new ones 8. The work of securing AI systems will never be complete By sharing these insights alongside case studies from our operations, we offer practical recommendations aimed at aligning red teaming efforts with real world risks. We also highlight aspects of AI red teaming that we believe are often misunderstood and discuss open questions for the field to consider.

Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared in the training samples, which hinders the achievement of satisfactory performance. To improve OOE-NER performance, in this paper, we propose a new framework, namely S+NER, which fully leverages sentence-level information. Our S+NER achieves better OOE-NER performance mainly due to the following two particular designs. 1) It first exploits the pre-trained language model's capability of understanding the target entity's sentence-level context with a template set. 2) Then, it refines the sentence-level representation based on the positive and negative templates, through a contrastive learning strategy and template pooling method, to obtain better NER results. Our extensive experiments on five benchmark datasets have demonstrated that, our S+NER outperforms some state-of-the-art OOE-NER models.

Detecting and classifying abnormal system states is critical for condition monitoring, but supervised methods often fall short due to the rarity of anomalies and the lack of labeled data. Therefore, clustering is often used to group similar abnormal behavior. However, evaluating cluster quality without ground truth is challenging, as existing measures such as the Silhouette Score (SSC) only evaluate the cohesion and separation of clusters and ignore possible prior knowledge about the data. To address this challenge, we introduce the Synchronized Anomaly Agreement Index (SAAI), which exploits the synchronicity of anomalies across multivariate time series to assess cluster quality. We demonstrate the effectiveness of SAAI by showing that maximizing SAAI improves accuracy on the task of finding the true number of anomaly classes K in correlated time series by 0.23 compared to SSC and by 0.32 compared to X-Means. We also show that clusters obtained by maximizing SAAI are easier to interpret compared to SSC.

Despite its importance, studying economic behavior across diverse, non-WEIRD (Western, Educated, Industrialized, Rich, and Democratic) populations presents significant challenges. We address this issue by introducing a novel methodology that uses Large Language Models (LLMs) to create synthetic cultural agents (SCAs) representing these populations. We subject these SCAs to classic behavioral experiments, including the dictator and ultimatum games. Our results demonstrate substantial cross-cultural variability in experimental behavior. Notably, for populations with available data, SCAs' behaviors qualitatively resemble those of real human subjects. For unstudied populations, our method can generate novel, testable hypotheses about economic behavior. By integrating AI into experimental economics, this approach offers an effective and ethical method to pilot experiments and refine protocols for hard-to-reach populations. Our study provides a new tool for cross-cultural economic studies and demonstrates how LLMs can help experimental behavioral research.

Question answering on free-form tables (a.k.a. TableQA) is a challenging task because of the flexible structure and complex schema of tables. Recent studies use Large Language Models (LLMs) for this task, exploiting their capability in understanding the questions and tabular data, which are typically given in natural language and contain many textual fields, respectively. While this approach has shown promising results, it overlooks the challenges brought by numerical values which are common in tabular data, and LLMs are known to struggle with such values. We aim to address this issue, and we propose a model named TabLaP that uses LLMs as a planner rather than an answer generator. This approach exploits LLMs' capability in multi-step reasoning while leaving the actual numerical calculations to a Python interpreter for accurate calculation. Recognizing the inaccurate nature of LLMs, we further make a first attempt to quantify the trustworthiness of the answers produced by TabLaP, such that users can use TabLaP in a regret-aware manner. Experimental results on two benchmark datasets show that TabLaP is substantially more accurate than the state-of-the-art models, improving the answer accuracy by 5.7% and 5.8% on the two datasets, respectively.

A hybrid framework integrating the Virtual Element Method (VEM) with deep learning is presented as an initial step toward developing efficient and flexible numerical models for one-dimensional Euler-Bernoulli beams. The primary aim is to explore a data-driven surrogate model capable of predicting displacement fields across varying material and geometric parameters while maintaining computational efficiency. Building upon VEM's ability to handle higher-order polynomials and non-conforming discretizations, the method offers a robust numerical foundation for structural mechanics. A neural network architecture is introduced to separately process nodal and material-specific data, effectively capturing complex interactions with minimal reliance on large datasets. To address challenges in training, the model incorporates Sobolev training and GradNorm techniques, ensuring balanced loss contributions and enhanced generalization. While this framework is in its early stages, it demonstrates the potential for further refinement and development into a scalable alternative to traditional methods. The proposed approach lays the groundwork for advancing numerical and data-driven techniques in beam modeling, offering a foundation for future research in structural mechanics.

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic balance, affecting the effectiveness of debiasing. With the rise of large language models and their extensive knowledge, we propose enhancing fairness (Fair-Gender) in PLMs by absorbing coherent, attribute-balanced, and semantically rich sentences. However, these sentences cannot be directly used for debiasing due to alignment issues and the risk of negative transfer. We address this by applying causal analysis to estimate causal effects, filtering out unaligned sentences, and identifying aligned ones for incorporation into PLMs, thereby ensuring positive transfer. Experiments show that our approach significantly reduces gender biases in PLMs while preserving their language expressiveness.

Automated drug discovery offers significant potential for accelerating the development of novel therapeutics by substituting labor-intensive human workflows with machine-driven processes. However, molecules generated by artificial intelligence may unintentionally infringe on existing patents, posing legal and financial risks that impede the full automation of drug discovery pipelines. This paper introduces PatentFinder, a novel multi-agent and tool-enhanced intelligence system that can accurately and comprehensively evaluate small molecules for patent infringement. PatentFinder features five specialized agents that collaboratively analyze patent claims and molecular structures with heuristic and model-based tools, generating interpretable infringement reports. To support systematic evaluation, we curate MolPatent-240, a benchmark dataset tailored for patent infringement assessment algorithms. On this benchmark, PatentFinder outperforms baseline methods that rely solely on large language models or specialized chemical tools, achieving a 13.8% improvement in F1-score and a 12% increase in accuracy. Additionally, PatentFinder autonomously generates detailed and interpretable patent infringement reports, showcasing enhanced accuracy and improved interpretability. The high accuracy and interpretability of PatentFinder make it a valuable and reliable tool for automating patent infringement assessments, offering a practical solution for integrating patent protection analysis into the drug discovery pipeline.

Mental health disorders pose a growing public health concern in the Arab world, emphasizing the need for accessible diagnostic and intervention tools. Large language models (LLMs) offer a promising approach, but their application in Arabic contexts faces challenges including limited labeled datasets, linguistic complexity, and translation biases. This study comprehensively evaluates 8 LLMs, including general multi-lingual models, as well as bi-lingual ones, on diverse mental health datasets (such as AraDepSu, Dreaddit, MedMCQA), investigating the impact of prompt design, language configuration (native Arabic vs. translated English, and vice versa), and few-shot prompting on diagnostic performance. We find that prompt engineering significantly influences LLM scores mainly due to reduced instruction following, with our structured prompt outperforming a less structured variant on multi-class datasets, with an average difference of 14.5\%. While language influence on performance was modest, model selection proved crucial: Phi-3.5 MoE excelled in balanced accuracy, particularly for binary classification, while Mistral NeMo showed superior performance in mean absolute error for severity prediction tasks. Few-shot prompting consistently improved performance, with particularly substantial gains observed for GPT-4o Mini on multi-class classification, boosting accuracy by an average factor of 1.58. These findings underscore the importance of prompt optimization, multilingual analysis, and few-shot learning for developing culturally sensitive and effective LLM-based mental health tools for Arabic-speaking populations.

As a former military intelligence officer, serving in the Defense Intelligence Agency (DIA), I tracked foreign threats to the U.S. homeland, identifying adversaries' plans, intentions and capabilities that could harm Americans. I predicted Russia's invasion of Ukraine more than a year before it took place. In March, in my Fox News Digital article titled "Ignore FBI director's urgent warning about terrorist threats at our own peril," I predicted terrorist attacks striking inside the U.S. homeland, the kind that took place on New Year's Day in New Orleans and in Las Vegas. Here are the top three reasons why we will likely face more terrorism in America this year. This time, it will be something we haven't seen before.