AI policy guidance is predominantly written as prose, which practitioners must first convert into executable rules before frameworks can evaluate or enforce them. This manual step is slow, error-prone, difficult to scale, and often delays the use of safeguards in real-world deployments. To address this gap, we present Policy-to-Tests (P2T), a framework that converts natural-language policy documents into normalized, machine-readable rules. The framework comprises a pipeline and a compact domain-specific language (DSL) that encodes hazards, scope, conditions, exceptions, and required evidence, yielding a canonical representation of extracted rules. To test the framework beyond a single policy, we apply it across general frameworks, sector guidance, and enterprise standards, extracting obligation-bearing clauses and converting them into executable rules. These AI-generated rules closely match strong human baselines on span-level and rule-level metrics, with robust inter-annotator agreement on the gold set. To evaluate downstream behavioral and safety impact, we add HIPAA-derived safeguards to a generative agent and compare it with an otherwise identical agent without guardrails. An LLM-based judge, aligned with gold-standard criteria, measures violation rates and robustness to obfuscated and compositional prompts. Detailed results are provided in the appendix. We release the codebase, DSL, prompts, and rule sets as open-source resources to enable reproducible evaluation.

Large Language Models perform well at natural language interpretation and reasoning, but their inherent stochasticity limits their adoption in regulated industries like finance and healthcare that operate under strict policies. To address this limitation, we present a two-stage neurosymbolic framework that (1) uses LLMs with optional human guidance to formalize natural language policies, allowing fine-grained control of the formalization process, and (2) uses inference-time autofor-malization to validate logical correctness of natural language statements against those policies. When correctness is paramount, we perform multiple redundant formalization steps at inference time, cross checking the formalizations for semantic equivalence. Our benchmarks demonstrate that our approach exceeds 99% soundness, indicating a near-zero false positive rate in identifying logical validity. Our approach produces auditable logical artifacts that substantiate the verification outcomes and can be used to improve the original text. The content generation and reasoning capabilities of Large Language Models (LLMs) continue to advance rapidly, demonstrating unprecedented improvements in coherence and analytical accuracy (Wei et al., 2022; Y ao et al., 2023; Lewis et al., 2021). Despite these advances, their probabilistic nature and tendency to generate plausible but incorrect information (hallucinations, cf. Xu et al. 2024b) remain barriers to widespread adoption in regulated sectors. Industries such as healthcare, financial services, and legal practices have legal and regulatory obligations for accuracy and auditability that current LLM technology has yet to meet (Haltaufderheide & Ranisch, 2024). Companies develop institutional policies to ensure compliance with applicable laws and regulations. Such policies are typically captured in natural language (NL) documents that define rules, procedures, or guidelines. A challenge thus emerges when organizations look to deploy LLMs to answer questions about such documents: can we develop guardrails to ensure that LLM outputs conform to institutional policies? Consider an airline implementing a chatbot to assist customer service representatives in navigating refund policies: if the chatbot incorrectly claims that a customer is eligible for a refund when they are not, this could lead to legal exposure and loss of customer trust. An effective guardrail would help representatives decide if they can rely on a chatbot response without spending additional human effort to verify it. The key concern would be to ensure that when the guardrail reports an answer is valid, it actually is.

Despite the importance of social science knowledge for various stakeholders, measuring its diffusion into different domains remains a challenge. This study uses a novel text-based approach to measure the idea-level diffusion of social science knowledge from the research domain to the journalism and policy-making domains. By doing so, we expand the detection of knowledge diffusion beyond the measurements of direct references. Our study focuses on media effects theories as key research ideas in the field of communication science. Using 72,703 documents (2000-2019) from three domains (i.e., research, journalism, and policy-making) that mention these ideas, we count the mentions of these ideas in each domain, estimate their domain-specific contexts, and track and compare differences across domains and over time. Overall, we find that diffusion patterns and dynamics vary considerably between ideas, with some ideas diffusing between other domains, while others do not. Based on the embedding regression approach, we compare contextualized meanings across domains and find that the distances between research and policy are typically larger than between research and journalism. We also find that ideas largely shift roles across domains - from being the theories themselves in research to sense-making in news to applied, administrative use in policy. Over time, we observe semantic convergence mainly for ideas that are practically oriented. Our results characterize the cross-domain diffusion patterns and dynamics of social science knowledge at the idea level, and we discuss the implications for measuring knowledge diffusion beyond citations.

Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10 leading commercial LLMs against both a novel 200-prompt CBRN dataset and a 180-prompt subset of the FORTRESS benchmark, using a rigorous three-tier attack methodology. Our findings expose critical safety vulnerabilities: Deep Inception attacks achieve 86.0\% success versus 33.8\% for direct requests, demonstrating superficial filtering mechanisms; Model safety performance varies dramatically from 2\% (claude-opus-4) to 96\% (mistral-small-latest) attack success rates; and eight models exceed 70\% vulnerability when asked to enhance dangerous material properties. We identify fundamental brittleness in current safety alignment, where simple prompt engineering techniques bypass safeguards for dangerous CBRN information. These results challenge industry safety claims and highlight urgent needs for standardized evaluation frameworks, transparent safety metrics, and more robust alignment techniques to mitigate catastrophic misuse risks while preserving beneficial capabilities.

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing internalization methods that embed policy documents into model priors while preserving performance. Prior prompt compression work targets generic prompts, but agentic policy documents span multiple complexity levels and require deeper reasoning, making internalization harder. We introduce CC-Gen, an agentic benchmark generator with Controllable Complexity across four levels, enabling systematic evaluation of agents' ability to handle complexity and offering a unified framework for assessing policy internalization. Our analysis shows that complex policy specifications governing workflows pose major reasoning challenges. Supporting internalization with gold user agent interaction trajectories containing chain-of-thought (CoT) annotations via supervised fine-tuning (SFT) is data-intensive and degrades sharply as policy complexity increases. To mitigate data and reasoning burdens, we propose Category-Aware Policy Continued Pretraining (CAP-CPT). Our automated pipeline parses policy documents to extract key specifications, grouping them into factual, behavioral, and conditional categories, and isolating complex conditions that drive workflow complexity. This guides targeted data synthesis and enables agents to internalize policy information through an autoregressive pretraining loss. Experiments show CAP-CPT improves SFT baselines in all settings, with up to 41% and 22% gains on Qwen-3-32B, achieving 97.3% prompt length reduction on CC-Gen and further enhancing tau-Bench with minimal SFT data.

We introduce CAPC-CG, the Chinese Adaptive Policy Communication (Central Government) Corpus, the first open dataset of Chinese policy directives annotated with a five-color taxonomy of clear and ambiguous language categories, building on Ang's theory of adaptive policy communication. Spanning 1949-2023, this corpus includes national laws, administrative regulations, and ministerial rules issued by China's top authorities. Each document is segmented into paragraphs, producing a total of 3.3 million units. Alongside the corpus, we release comprehensive metadata, a two-round labeling framework, and a gold-standard annotation set developed by expert and trained coders. Inter-annotator agreement achieves a Fleiss's kappa of K = 0.86 on directive labels, indicating high reliability for supervised modeling. We provide baseline classification results with several large language models (LLMs), together with our annotation codebook, and describe patterns from the dataset. This release aims to support downstream tasks and multilingual NLP research in policy communication.

Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company policies. In this study we introduce a deterministic, transparent, and modular framework for enforcing business policy adherence in agentic workflows. Our method operates in two phases: (1) an offline buildtime stage that compiles policy documents into verifiable guard code associated with tool use, and (2) a runtime integration where these guards ensure compliance before each agent action. We demonstrate our approach on the challenging $τ$-bench Airlines domain, showing encouraging preliminary results in policy enforcement, and further outline key challenges for real-world deployments.

The upsurge of policies and guidelines that aim to ensure Artificial Intelligence (AI) systems are safe and trustworthy has led to a fragmented landscape of AI governance. The European Union (EU) is a key actor in the development of such policies and guidelines. Its High-Level Expert Group (HLEG) issued an influential set of guidelines for trustworthy AI, followed in 2024 by the adoption of the EU AI Act. While the EU policies and guidelines are expected to be aligned, they may differ in their scope, areas of emphasis, degrees of normativity, and priorities in relation to AI. To gain a broad understanding of AI governance from the EU perspective, we leverage qualitative thematic analysis approaches to uncover prevalent themes in key EU documents, including the AI Act and the HLEG Ethics Guidelines. We further employ quantitative topic modelling approaches, specifically through the use of the BERTopic model, to enhance the results and increase the document sample to include EU AI policy documents published post-2018. We present a novel perspective on EU policies, tracking the evolution of its approach to addressing AI governance.

After natural disasters, accurate evaluations of damage to housing are important for insurance claims response and planning of resources. In this work, we introduce a novel multimodal retrieval-augmented generation (MM-RAG) framework. On top of classical RAG architecture, we further the framework to devise a two-branch multimodal encoder structure that the image branch employs a visual encoder composed of ResNet and Transformer to extract the characteristic of building damage after disaster, and the text branch harnesses a BERT retriever for the text vectorization of posts as well as insurance policies and for the construction of a retrievable restoration index. To impose cross-modal semantic alignment, the model integrates a cross-modal interaction module to bridge the semantic representation between image and text via multi-head attention. Meanwhile, in the generation module, the introduced modal attention gating mechanism dynamically controls the role of visual evidence and text prior information during generation. The entire framework takes end-to-end training, and combines the comparison loss, the retrieval loss and the generation loss to form multi-task optimization objectives, and achieves image understanding and policy matching in collaborative learning. The results demonstrate superior performance in retrieval accuracy and classification index on damage severity, where the Top-1 retrieval accuracy has been improved by 9.6%.

A backlash is brewing against Meta over what it permits its AI chatbots to say. An internal Meta policy document, seen by Reuters, showed the social media giant's guidelines for its chatbots allowed the AI to "engage a child in conversations that are romantic or sensual", generate false medical information, and assist users in arguing that Black people are "dumber than white people". Singer Neil Young quit the social media platform on Friday, his record company said in a statement, the latest in a string of the singer's online-oriented protests. "At Neil Young's request, we are no longer using Facebook for any Neil Young related activities," Reprise Records announced. "Meta's use of chatbots with children is unconscionable. Mr. Young does not want a further connection with Facebook."