As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical. While prior work has largely focused on improving LLM performance in these domains, it has often neglected the evaluation of domain-specific safety risks. To bridge this gap, we first define domain-specific safety principles for LLMs based on the AMA Principles of Medical Ethics, the ABA Model Rules of Professional Conduct, and the CFA Institute Code of Ethics. Building on this foundation, we introduce Trident-Bench, a benchmark specifically targeting LLM safety in the legal, financial, and medical domains. We evaluated 19 general-purpose and domain-specialized models on Trident-Bench and show that it effectively reveals key safety gaps -- strong generalist models (e.g., GPT, Gemini) can meet basic expectations, whereas domain-specialized models often struggle with subtle ethical nuances. This highlights an urgent need for finer-grained domain-specific safety improvements. By introducing Trident-Bench, our work provides one of the first systematic resources for studying LLM safety in law and finance, and lays the groundwork for future research aimed at reducing the safety risks of deploying LLMs in professionally regulated fields. Code and benchmark will be released at: https://github.com/zackhuiiiii/TRIDENT

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390 experimental responses from three major LLMs (Claude, GPT-4, Gemini) across 10 task domains under 6 threat conditions. We introduce a novel threat taxonomy and multi-metric evaluation framework to quantify both negative manipulation effects and positive performance improvements. Results reveal systematic vulnerabilities, with policy evaluation showing the highest metric significance rates under role-based threats, alongside substantial performance enhancements in numerous cases with effect sizes up to +1336%. Statistical analysis indicates systematic certainty manipulation (pFDR < 0.0001) and significant improvements in analytical depth and response quality. These findings have dual implications for AI safety and practical prompt engineering in high-stakes applications.

Large Language Models (LLMs) are increasingly consulted for high-stakes life advice, yet they lack standard safeguards against providing confident but misguided responses. This creates risks of sycophancy and over-confidence. This paper investigates these failure modes through three experiments: (1) a multiple-choice evaluation to measure model stability against user pressure; (2) a free-response analysis using a novel safety typology and an LLM Judge; and (3) a mechanistic interpretability experiment to steer model behavior by manipulating a "high-stakes" activation vector. Our results show that while some models exhibit sycophancy, others like o4-mini r emain robust. Top-performing models achieve high safety scores by frequently asking clarifying questions--a key feature of a safe, inquisitive approach--rather than issuing prescriptive advice . Furthermore, we demonstrate that a model's cautiousness can be directly controlled via activation steering, suggesting a new path for safety alignment. These findings underscore the need for nuanced, multi-faceted benchmarks to ensure LLMs can be trusted with life-changing decisions.

Unlike prior approaches that treat alignment as a static or post-hoc property, NPO introduces a formalization of alignment loss that is measurable, supervisable, and reducible under structured feedback. In parallel, we propose meta-alignment as the fidelity of the monitoring process that governs retraining or override triggers, and show that it is formally reducible to primary alignment via threshold fidelity. Our implementation spans a scalable operational loop involving scenario scoring, threshold tuning, policy validation, and structured feedback ingestion, including "likes," overrides, and abstentions. We provide formal convergence results under stochastic feedback and show that both alignment loss and monitoring fidelity converge additively. Empirically, NPO demonstrates measurable value in hyperscale deployment settings. A simulation-based artifact and ablation studies further illustrate the theoretical principles in action. Together, NPO offers a compact, inspectable architecture for continual alignment monitoring, helping bridge theoretical alignment guarantees with practical reliability in dynamic environments.

We present INTEGRALBENCH, a focused benchmark designed to evaluate Large Language Model (LLM) performance on definite integral problems. INTEGRALBENCH provides both symbolic and numerical ground truth solutions with manual difficulty annotations. Our evaluation of nine state-of-the-art LLMs reveals significant performance gaps and strong correlations between problem difficulty and model accuracy, establishing baseline metrics for this challenging domain. INTEGRALBENCH aims to advance automated mathematical reasoning by providing a rigorous evaluation framework specifically tailored for definite integral computation.

In an era of radical technology transformations, technology maps play a crucial role in enhancing decision making. These maps heavily rely on automated methods of technology extraction. This paper introduces Retrieval Augmented Technology Extraction (RATE), a Large Language Model (LLM) based pipeline for automated technology extraction from scientific literature. RATE combines Retrieval Augmented Generation (RAG) with multi-definition LLM-based validation. This hybrid method results in high recall in candidate generation alongside with high precision in candidate filtering. While the pipeline is designed to be general and widely applicable, we demonstrate its use on 678 research articles focused on Brain-Computer Interfaces (BCIs) and Extended Reality (XR) as a case study. Consequently, The validated technology terms by RATE were mapped into a co-occurrence network, revealing thematic clusters and structural features of the research landscape. For the purpose of evaluation, a gold standard dataset of technologies in 70 selected random articles had been curated by the experts. In addition, a technology extraction model based on Bidirectional Encoder Representations of Transformers (BERT) was used as a comparative method. RATE achieved F1-score of 91.27%, Significantly outperforming BERT with F1-score of 53.73%. Our findings highlight the promise of definition-driven LLM methods for technology extraction and mapping. They also offer new insights into emerging trends within the BCI-XR field. The source code is available https://github.com/AryaAftab/RATE

We present VizGenie, a self-improving, agentic framework that advances scientific visualization through large language model (LLM) by orchestrating of a collection of domain-specific and dynamically generated modules. Users initially access core functionalities--such as threshold-based filtering, slice extraction, and statistical analysis--through pre-existing tools. For tasks beyond this baseline, VizGenie autonomously employs LLMs to generate new visualization scripts (e.g., VTK Python code), expanding its capabilities on-demand. Each generated script undergoes automated backend validation and is seamlessly integrated upon successful testing, continuously enhancing the system's adaptability and robustness. A distinctive feature of VizGenie is its intuitive natural language interface, allowing users to issue high-level feature-based queries (e.g., ``visualize the skull"). The system leverages image-based analysis and visual question answering (VQA) via fine-tuned vision models to interpret these queries precisely, bridging domain expertise and technical implementation. Additionally, users can interactively query generated visualizations through VQA, facilitating deeper exploration. Reliability and reproducibility are further strengthened by Retrieval-Augmented Generation (RAG), providing context-driven responses while maintaining comprehensive provenance records. Evaluations on complex volumetric datasets demonstrate significant reductions in cognitive overhead for iterative visualization tasks. By integrating curated domain-specific tools with LLM-driven flexibility, VizGenie not only accelerates insight generation but also establishes a sustainable, continuously evolving visualization practice. The resulting platform dynamically learns from user interactions, consistently enhancing support for feature-centric exploration and reproducible research in scientific visualization.

This paper explores the use of large language models (LLMs) to assist in the development of new disease modules for Synthea, an open-source synthetic health data generator. Incorporating LLMs into the module development process has the potential to reduce development time, reduce required expertise, expand model diversity, and improve the overall quality of synthetic patient data. We demonstrate four ways that LLMs can support Synthea module creation: generating a disease profile, generating a disease module from a disease profile, evaluating an existing Synthea module, and refining an existing module. We introduce the concept of progressive refinement, which involves iteratively evaluating the LLM-generated module by checking its syntactic correctness and clinical accuracy, and then using that information to modify the module. While the use of LLMs in this context shows promise, we also acknowledge the challenges and limitations, such as the need for human oversight, the importance of rigorous testing and validation, and the potential for inaccuracies in LLM-generated content. The paper concludes with recommendations for future research and development to fully realize the potential of LLM-aided synthetic data creation.

Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges for manual sorting and analysis. These archives contain diverse content, including various text types (handwritten, typed, printed), graphical elements (drawings, maps, photos), and layouts (plain text, tables, forms). Efficiently processing this heterogeneous data requires automated methods to categorize pages based on their content, enabling tailored downstream analysis pipelines. This project addresses this need by developing and evaluating an image classification system specifically designed for historical document pages, leveraging advancements in artificial intelligence and machine learning. The set of categories was chosen to facilitate content-specific processing workflows, separating pages requiring different analysis techniques (e.g., OCR for text, image analysis for graphics)

This paper introduces SemRAG, an enhanced Retrieval Augmented Generation (RAG) framework that efficiently integrates domain-specific knowledge using semantic chunking and knowledge graphs without extensive fine-tuning. Integrating domain-specific knowledge into large language models (LLMs) is crucial for improving their performance in specialized tasks. Yet, existing adaptations are computationally expensive, prone to overfitting and limit scalability. To address these challenges, SemRAG employs a semantic chunking algorithm that segments documents based on the cosine similarity from sentence embeddings, preserving semantic coherence while reducing computational overhead. Additionally, by structuring retrieved information into knowledge graphs, SemRAG captures relationships between entities, improving retrieval accuracy and contextual understanding. Experimental results on MultiHop RAG and Wikipedia datasets demonstrate SemRAG has significantly enhances the relevance and correctness of retrieved information from the Knowledge Graph, outperforming traditional RAG methods. Furthermore, we investigate the optimization of buffer sizes for different data corpus, as optimizing buffer sizes tailored to specific datasets can further improve retrieval performance, as integration of knowledge graphs strengthens entity relationships for better contextual comprehension. The primary advantage of SemRAG is its ability to create an efficient, accurate domain-specific LLM pipeline while avoiding resource-intensive fine-tuning. This makes it a practical and scalable approach aligned with sustainability goals, offering a viable solution for AI applications in domain-specific fields.