This paper provides an experimental evaluation of the capability of large language models (LLMs) to assist in legal decision-making within the framework of Austrian and European Union value-added tax (VAT) law. In tax consulting practice, clients often describe cases in natural language, making LLMs a prime candidate for supporting automated decision-making and reducing the workload of tax professionals. Given the requirement for legally grounded and well-justified analyses, the propensity of LLMs to hallucinate presents a considerable challenge. The experiments focus on two common methods for enhancing LLM performance: fine-tuning and retrieval-augmented generation (RAG). In this study, these methods are applied on both textbook cases and real-world cases from a tax consulting firm to systematically determine the best configurations of LLM-based systems and assess the legal-reasoning capabilities of LLMs. The findings highlight the potential of using LLMs to support tax consultants by automating routine tasks and providing initial analyses, although current prototypes are not ready for full automation due to the sensitivity of the legal domain. The findings indicate that LLMs, when properly configured, can effectively support tax professionals in VAT tasks and provide legally grounded justifications for decisions. However, limitations remain regarding the handling of implicit client knowledge and context-specific documentation, underscoring the need for future integration of structured background information.

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates. By automatically extracting logical patterns from structured knowledge bases and aligning them with LLMs' internal logics, ChainEdit dynamically generates and edits logically connected knowledge clusters. Experiments demonstrate an improvement of more than 30% in logical generalization over baselines while preserving editing reliability and specificity. We further address evaluation biases in existing benchmarks through knowledge-aware protocols that disentangle external dependencies. This work establishes new state-of-the-art performance on ripple effect while ensuring internal logical consistency after knowledge editing.

Language models are prone to hallucination - generating text that is factually incorrect. Finetuning models on high-quality factual information can potentially reduce hallucination, but concerns remain; obtaining factual gold data can be expensive and training on correct but unfamiliar data may potentially lead to even more downstream hallucination. What data should practitioners finetune on to mitigate hallucinations in language models? In this work, we study the relationship between the factuality of finetuning data and the prevalence of hallucinations in long-form generation tasks. Counterintuitively, we find that finetuning on factual gold data is not as helpful as finetuning on model-generated data that models believe to be factual. Next, we evaluate filtering strategies applied on both factual gold data and model-generated data, and find that finetuning on model-generated data that is filtered by models' own internal judgments often leads to better overall factuality compared to other configurations: training on gold data filtered by models' judgments, training on gold data alone, or training on model-generated data that is supported by gold data. These factuality improvements transfer across three domains we study, suggesting that a models' own beliefs can provide a powerful signal for factuality.

There is growing interest in giving AI agents access to cryptocurrencies as well as to the smart contracts that transact them. But doing so, this position paper argues, could lead to formidable new vectors of AI harm. To support this argument, we first examine the unique properties of cryptocurrencies and smart contracts that could lead to these new vectors of harm. Next, we describe each of these new vectors of harm in detail. Finally, we conclude with a call for more technical research aimed at preventing and mitigating these harms and, thereby making it safer to endow AI agents with cryptocurrencies and smart contracts.

Quantum neural networks (QNN) hold immense potential for the future of quantum machine learning (QML). However, QNN security and robustness remain largely unexplored. In this work, we proposed novel Trojan attacks based on the quantum computing properties in a QNN-based binary classifier. Our proposed Quantum Properties Trojans (QuPTs) are based on the unitary property of quantum gates to insert noise and Hadamard gates to enable superposition to develop Trojans and attack QNNs. We showed that the proposed QuPTs are significantly stealthier and heavily impact the quantum circuits' performance, specifically QNNs. The most impactful QuPT caused a deterioration of 23% accuracy of the compromised QNN under the experimental setup. To the best of our knowledge, this is the first work on the Trojan attack on a fully quantum neural network independent of any hybrid classical-quantum architecture.

As cyber-physical systems grow increasingly interconnected and spatially distributed, ensuring their resilience against evolving cyberattacks has become a critical priority. Spatio-Temporal Anomaly detection plays an important role in ensuring system security and operational integrity. However, current data-driven approaches, largely driven by black-box deep learning, face challenges in interpretability, adaptability to distribution shifts, and robustness under evolving system dynamics. In this paper, we advocate for a causal learning perspective to advance anomaly detection in spatially distributed infrastructures that grounds detection in structural cause-effect relationships. We identify and formalize three key directions: causal graph profiling, multi-view fusion, and continual causal graph learning, each offering distinct advantages in uncovering dynamic cause-effect structures across time and space. Drawing on real-world insights from systems such as water treatment infrastructures, we illustrate how causal models provide early warning signals and root cause attribution, addressing the limitations of black-box detectors. Looking ahead, we outline the future research agenda centered on multi-modality, generative AI-driven, and scalable adaptive causal frameworks. Our objective is to lay a new research trajectory toward scalable, adaptive, explainable, and spatially grounded anomaly detection systems. We hope to inspire a paradigm shift in cybersecurity research, promoting causality-driven approaches to address evolving threats in interconnected infrastructures.

The emergence of large language models (LLMs) and agentic systems is enabling autonomous 6G networks with advanced intelligence, including self-configuration, self-optimization, and self-healing. However, the current implementation of individual intelligence tasks necessitates isolated knowledge retrieval pipelines, resulting in redundant data flows and inconsistent interpretations. Inspired by the service model unification effort in Open-RAN (to support interoperability and vendor diversity), we propose KP-A: a unified Network Knowledge Plane specifically designed for Agentic network intelligence. By decoupling network knowledge acquisition and management from intelligence logic, KP-A streamlines development and reduces maintenance complexity for intelligence engineers. By offering an intuitive and consistent knowledge interface, KP-A also enhances interoperability for the network intelligence agents. We demonstrate KP-A in two representative intelligence tasks: live network knowledge Q&A and edge AI service orchestration. All implementation artifacts have been open-sourced to support reproducibility and future standardization efforts.

Traffic accidents are rare, yet high-impact events that require long-context multimodal reasoning for accurate risk forecasting. In this paper, we introduce ALCo-FM, a unified adaptive long-context foundation model that computes a volatility pre-score to dynamically select context windows for input data and encodes and fuses these multimodal data via shallow cross attention. Following a local GAT layer and a BigBird-style sparse global transformer over H3 hexagonal grids, coupled with Monte Carlo dropout for confidence, the model yields superior, well-calibrated predictions. Trained on data from 15 US cities with a class-weighted loss to counter label imbalance, and fine-tuned with minimal data on held-out cities, ALCo-FM achieves 0.94 accuracy, 0.92 F1, and an ECE of 0.04, outperforming more than 20 state-of-the-art baselines in large-scale urban risk prediction. Code and dataset are available at: https://github.com/PinakiPrasad12/ALCo-FM

Contemporary organizations have shown great interest in integrating language models (LMs) into workflows traditionally performed by human subject matter experts (SMEs), such as in medical diagnostics (Artsi et al., 2025), legal assistance (Padiu et al., 2024), financial risk analysis (AI21 labs, 2025), and governmental permitting or regulatory reviews (Phan et al., 2024). Despite this interest, however, the use of LMs (e.g., via a standard conversational interface) in high-stakes contexts is constrained by the need for decision-making reliability, objectivity, transparency, and accountability that SMEs currently provide (Mori, 2024). Effective reconciliation between LMs and SMEs thus represents a critical frontier in real-world deployments of artificial intelligence. LMs have demonstrated remarkable capabilities in extracting information from large volumes of multi-modal, multi-domain data; synthesizing multi-document concepts; and performing tasks associated with basic reasoning. Nonetheless, LMs are susceptible to "hallucinations" (i.e., inaccurate generation) (Ji et al., 2023), difficulty in handling nuanced, domain-specific requirements (Ashqar, 2025), historical biases inherited from training data (Ranjan et al., 2024), and opaque reasoning in decision-making (Machot et al., 2024). Notably, these weaknesses are often precisely the strengths of SMEs, who are conversely burdened with the inefficient and labor-intensive tasks of cross-document, multi-modal search and information extraction. We can see the need to delineate and integrate the often low-stakes or tedious work that can be performed by LMs with the discerning, high-stakes decision-making tasks performed by SMEs in the real world: The challenge is to harness the time efficiency and broad knowledge capabilities of LMs while preserving the domain expertise, contextual judgment, oversight, and accountability of SMEs. Moreover, we must do so without creating additional burdens for SMEs to work with LMs (e.g., "prompt-engineering" or manual review of all LM tasks), and we wish to minimize the introduction of new risks (e.g., a loss of clarity regarding where or how LMs may be used by each SME, or, in the case of governmental work, the erosion of public trust). In this work, we propose a novel auditable and interactive refinement framework for the effective integration of LMs with SMEs for decision-making workflows.

Social media has amplified the reach of financial influencers known as "finfluencers," who share stock recommendations on platforms like YouTube. Understanding their influence requires analyzing multimodal signals like tone, delivery style, and facial expressions, which extend beyond text-based financial analysis. We introduce VideoConviction, a multimodal dataset with 6,000+ expert annotations, produced through 457 hours of human effort, to benchmark multimodal large language models (MLLMs) and text-based large language models (LLMs) in financial discourse. Our results show that while multimodal inputs improve stock ticker extraction (e.g., extracting Apple's ticker AAPL), both MLLMs and LLMs struggle to distinguish investment actions and conviction--the strength of belief conveyed through confident delivery and detailed reasoning--often misclassifying general commentary as definitive recommendations. While high-conviction recommendations perform better than low-conviction ones, they still underperform the popular S\&P 500 index fund. An inverse strategy--betting against finfluencer recommendations--outperforms the S\&P 500 by 6.8\% in annual returns but carries greater risk (Sharpe ratio of 0.41 vs. 0.65). Our benchmark enables a diverse evaluation of multimodal tasks, comparing model performance on both full video and segmented video inputs. This enables deeper advancements in multimodal financial research. Our code, dataset, and evaluation leaderboard are available under the CC BY-NC 4.0 license.