Table 9) and identifying reflections (Error #20 in Table 13) are also noted.

Here is a breakdown of the three steps involved: 1) Prototype: We utilize CLIP to encode a collection of text prompts obtained from social media platforms that express similar negative concepts. These encoded features are then aggregated into a comprehensive prototype feature, capturing the semantics of the negative concepts.

This section illustrates how a model's performance may vary across different tasks associated with We analyzed the performance of Llama-3-Instruct-70B on the new term "wokely," The book's cover was described as wokely by several reviewers. A. it struggled to attract attention on the bookstore displays despite a B. many readers were enticed to buy it, strengthening its presence on C. readers were intrigued and the book's sales experienced an unexpected surge worldwide. D. the publisher decided to release a limited edition with a special In the previous sentence, does _ refer to A. Is this example in line with commonsense and grammatically correct? As observed, the model only answered correctly in the COMA task but failed in the other two tasks. In the COMA task, the model successfully inferred that "wokely" carries a negative connotation, Although the phrase "hard to find a satisfying These results provide a comprehensive evaluation of the model's understanding of the term "wokely."

Large vision-language model (LVLM) based text-to-image (T2I) systems have become the dominant paradigm in image generation, yet whether they amplify social biases remains insufficiently understood. In this paper, we show that LVLM-based models produce markedly more socially biased images than non-LVLM-based models. We introduce a 1,024 prompt benchmark spanning four levels of linguistic complexity and evaluate demographic bias across multiple attributes in a systematic manner. Our analysis identifies system prompts, the predefined instructions guiding LVLMs, as a primary driver of biased behavior. Through decoded intermediate representations, token-probability diagnostics, and embedding-association analyses, we reveal how system prompts encode demographic priors that propagate into image synthesis. To this end, we propose FairPro, a training-free meta-prompting framework that enables LVLMs to self-audit and construct fairness-aware system prompts at test time. Experiments on two LVLM-based T2I models, SANA and Qwen-Image, show that FairPro substantially reduces demographic bias while preserving text-image alignment. We believe our findings provide deeper insight into the central role of system prompts in bias propagation and offer a practical, deployable approach for building more socially responsible T2I systems.

As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources (e.g., model developers, users, and tools) within a single prompt context. Thus, enforcing an instruction hierarchy (IH) in LLMs, where higher-level directives override lower-priority requests, is critical for the reliability and controllability of LLMs. In this work, we reframe instruction hierarchy resolution as a reasoning task. Specifically, the model must first "think" about the relationship between a given user prompt and higher-priority (system) instructions before generating a response. To enable this capability via training, we construct VerIH, an instruction hierarchy dataset of constraint-following tasks with verifiable answers. This dataset comprises ~7K aligned and conflicting system-user instructions. We show that lightweight reinforcement learning with VerIH effectively transfers general reasoning capabilities of models to instruction prioritization. Our finetuned models achieve consistent improvements on instruction following and instruction hierarchy benchmarks, achieving roughly a 20% improvement on the IHEval conflict setup. This reasoning ability also generalizes to safety-critical settings beyond the training distribution. By treating safety issues as resolving conflicts between adversarial user inputs and predefined higher-priority policies, our trained model enhances robustness against jailbreak and prompt injection attacks, providing up to a 20% reduction in attack success rate (ASR). These results demonstrate that reasoning over instruction hierarchies provides a practical path to reliable LLMs, where updates to system prompts yield controllable and robust changes in model behavior.

Advances in 3D generative AI have enabled the creation of physical objects from text prompts, but challenges remain in creating objects involving multiple component types. We present a pipeline that integrates 3D generative AI with vision-language models (VLMs) to enable the robotic assembly of multi-component objects from natural language. Our method leverages VLMs for zero-shot, multi-modal reasoning about geometry and functionality to decompose AI-generated meshes into multi-component 3D models using predefined structural and panel components. We demonstrate that a VLM is capable of determining which mesh regions need panel components in addition to structural components, based on the object's geometry and functionality. Evaluation across test objects shows that users preferred the VLM-generated assignments 90.6% of the time, compared to 59.4% for rule-based and 2.5% for random assignment. Lastly, the system allows users to refine component assignments through conversational feedback, enabling greater human control and agency in making physical objects with generative AI and robotics.

The application of machine learning (ML) methods, a subfield of artificial intelligence (AI), to the solution of electromagnetic boundary value problems (BVPs) is currently a highly active area of research. Deep neural networks such as neural operators (Kovachki et al. 2023) and physics-informed neural networks, in which information about the BVP (and possibly measurement data) is integrated into the loss function of the network, often aim to replace traditional numerical methods such as the finite element (FE) method, compare, for example, with (Guo et al. 2025; Rezende and Schuhmann 2025). This work addresses an orthogonal problem: How can AI methods be used to reduce the time required to set up electromagnetic simulation models, rather than solving the numerical models themselves? The focus is thus on the assisted generation of simulation models, whereby the numerical scheme itself remains unaffected. A conceptually related direction has recently emerged in the computational fluid dynamics (CFD) community.

Data analysis and performance evaluation of simulation deduction plays a pivotal role in modern warfare, which enables military personnel to gain invaluable insights into the potential effectiveness of different strategies, tactics, and operational plans. Traditional manual analysis approach is time-consuming and limited by human errors. To enhance efficiency and accuracy, large language models (LLMs) with strong analytical and inferencing capabilities can be employed. However, high-quality analysis reports with well-structured formatting cannot be obtained through a single instruction input to the LLM. To tackle this issue, we propose a method that first decomposes the complex task into several sub-tasks and designs effective system prompts and user prompts for each sub-task. Multi-round interactions with the LLM incorporating self-check and reflection are then conducted to enable structured data extraction as well as multi-step analysis and evaluation. Furthermore, custom tools are defined and invoked to generate figures and compute metrics. We also design multiple report templates, each tailored to a specific application and input data type, ensuring their adaptability across a variety of scenarios. Extensive evaluation results demonstrate that the reports generated by our method exhibit higher quality, therefore obtaining higher scores than the baseline method.