Resource distribution is a fundamental problem in economic and policy design, particularly when demand and supply are not naturally aligned. Without regulation, wealthier individuals may monopolize this resource, leaving the needs of others unsatisfied. While centralized distribution can ensure fairer division, it can struggle to manage logistics efficiently, and adapt to changing conditions, often leading to shortages, surpluses, and bureaucratic inefficiencies. Building on previous research on market-based redistribution, we examine a repeated hybrid market that incorporates buying rights. These rights, distributed iteratively by a central authority (for instance, as digital tokens), are intended to enhance fairness in the system - a unit of right is required to acquire a unit of the resource, but the rights themselves can also be traded alongside the resource in the market. We analyze how this regulatory mechanism influences the distribution of the scarce resource in the hybrid market over time. Unlike past works that relied on empirical methods, we explore the exact analytical properties of a system in which traders optimize over multiple rounds. We identify its market equilibrium, which is a natural generalization of the free market equilibrium, and show that it is coalition-proof. To assess the fairness in the system, we use the concept of frustration, which measures the gap between the resources a buyer is entitled to through their buying rights and what they actually obtain through trading. Our main theoretical result shows that using buying rights reduces the frustration by at least half compared to the free market. Empirical evaluations further support our findings, suggesting the system performs well even beyond the theoretically studied assumptions.

The introduction of the AI Act in the European Union presents the AI research and practice community with a set of new challenges related to compliance. While it is certain that AI practitioners will require additional guidance and tools to meet these requirements, previous research on toolkits that aim to translate the theory of AI ethics into development and deployment practice suggests that such resources suffer from multiple limitations. These limitations stem, in part, from the fact that the toolkits are either produced by industry-based teams or by academics whose work tends to be abstract and divorced from the realities of industry. In this paper, we discuss the challenge of developing an AI ethics toolkit for practitioners that helps them comply with new AI-focused regulation, but that also moves beyond mere compliance to consider broader socio-ethical questions throughout development and deployment. The toolkit was created through a cross-sectoral collaboration between an academic team based in the UK and an industry team in Italy. We outline the background and rationale for creating a pro-justice AI Act compliance toolkit, detail the process undertaken to develop it, and describe the collaboration and negotiation efforts that shaped its creation. We aim for the described process to serve as a blueprint for other teams navigating the challenges of academia-industry partnerships and aspiring to produce usable and meaningful AI ethics resources.

This work presents LURK (Latent UnleaRned Knowledge), a novel framework that probes for hidden retained knowledge in unlearned LLMs through adversarial suffix prompting. LURK automatically generates adversarial prompt suffixes designed to elicit residual knowledge about the Harry Potter domain, a commonly used benchmark for unlearning. Our experiments reveal that even models deemed successfully unlearned can leak idiosyncratic information under targeted adversarial conditions, highlighting critical limitations of current unlearning evaluation standards. By uncovering latent knowledge through indirect probing, LURK offers a more rigorous and diagnostic tool for assessing the robustness of unlearning algorithms. All code will be publicly available.

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more prone to produce harmful responses. In this paper, we propose the \textbf{M}ulti-\textbf{T}urn \textbf{S}afety \textbf{A}lignment (\ourapproach) framework, to address the challenge of securing LLMs in multi-round interactions. It consists of two stages: In the thought-guided attack learning stage, the red-team model learns about thought-guided multi-round jailbreak attacks to generate adversarial prompts. In the adversarial iterative optimization stage, the red-team model and the target model continuously improve their respective capabilities in interaction. Furthermore, we introduce a multi-turn reinforcement learning algorithm based on future rewards to enhance the robustness of safety alignment. Experimental results show that the red-team model exhibits state-of-the-art attack capabilities, while the target model significantly improves its performance on safety benchmarks.

The widespread use of Large Multimodal Models (LMMs) has raised concerns about model toxicity. However, current research mainly focuses on explicit toxicity, with less attention to some more implicit toxicity regarding prejudice and discrimination. To address this limitation, we introduce a subtler type of toxicity named dual-implicit toxicity and a novel toxicity benchmark termed MDIT-Bench: Multimodal Dual-Implicit Toxicity Benchmark. Specifically, we first create the MDIT-Dataset with dual-implicit toxicity using the proposed Multi-stage Human-in-loop In-context Generation method. Based on this dataset, we construct the MDIT-Bench, a benchmark for evaluating the sensitivity of models to dual-implicit toxicity, with 317,638 questions covering 12 categories, 23 subcategories, and 780 topics. MDIT-Bench includes three difficulty levels, and we propose a metric to measure the toxicity gap exhibited by the model across them. In the experiment, we conducted MDIT-Bench on 13 prominent LMMs, and the results show that these LMMs cannot handle dual-implicit toxicity effectively. The model's performance drops significantly in hard level, revealing that these LMMs still contain a significant amount of hidden but activatable toxicity. Data are available at https://github.com/nuo1nuo/MDIT-Bench.

This study examines cultural value alignment in large language models (LLMs) by analyzing how Gemini, ChatGPT, and DeepSeek prioritize values from Schwartz's value framework. Using the 40-item Portrait Values Questionnaire, we assessed whether DeepSeek, trained on Chinese-language data, exhibits distinct value preferences compared to Western models. Results of a Bayesian ordinal regression model show that self-transcendence values (e.g., benevolence, universalism) were highly prioritized across all models, reflecting a general LLM tendency to emphasize prosocial values. However, DeepSeek uniquely downplayed self-enhancement values (e.g., power, achievement) compared to ChatGPT and Gemini, aligning with collectivist cultural tendencies. These findings suggest that LLMs reflect culturally situated biases rather than a universal ethical framework. To address value asymmetries in LLMs, we propose multi-perspective reasoning, self-reflective feedback, and dynamic contextualization. This study contributes to discussions on AI fairness, cultural neutrality, and the need for pluralistic AI alignment frameworks that integrate diverse moral perspectives.

While tool learning significantly enhances the capabilities of large language models (LLMs), it also introduces substantial security risks. Prior research has revealed various vulnerabilities in traditional LLMs during tool learning. However, the safety of newly emerging reasoning LLMs (RLLMs), such as DeepSeek-R1, in the context of tool learning remains underexplored. To bridge this gap, we propose RRTL, a red teaming approach specifically designed to evaluate RLLMs in tool learning. It integrates two novel strategies: (1) the identification of deceptive threats, which evaluates the model's behavior in concealing the usage of unsafe tools and their potential risks; and (2) the use of Chain-of-Thought (CoT) prompting to force tool invocation. Our approach also includes a benchmark for traditional LLMs. We conduct a comprehensive evaluation on seven mainstream RLLMs and uncover three key findings: (1) RLLMs generally achieve stronger safety performance than traditional LLMs, yet substantial safety disparities persist across models; (2) RLLMs can pose serious deceptive risks by frequently failing to disclose tool usage and to warn users of potential tool output risks; (3) CoT prompting reveals multi-lingual safety vulnerabilities in RLLMs. Our work provides important insights into enhancing the security of RLLMs in tool learning.

This chapter explores the evolution, classification, and health implications of food processing, while emphasizing the transformative role of machine learning, artificial intelligence (AI), and data science in advancing food informatics. It begins with a historical overview and a critical review of traditional classification frameworks such as NOVA, Nutri-Score, and SIGA, highlighting their strengths and limitations, particularly the subjectivity and reproducibility challenges that hinder epidemiological research and public policy. To address these issues, the chapter presents novel computational approaches, including FoodProX, a random forest model trained on nutrient composition data to infer processing levels and generate a continuous FPro score. It also explores how large language models like BERT and BioBERT can semantically embed food descriptions and ingredient lists for predictive tasks, even in the presence of missing data. A key contribution of the chapter is a novel case study using the Open Food Facts database, showcasing how multimodal AI models can integrate structured and unstructured data to classify foods at scale, offering a new paradigm for food processing assessment in public health and research.

Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it faces fundamental challenges from censored sales data during stockouts, where unobserved demand creates systemic policy biases. Existing datasets lack the temporal resolution and annotations needed to address this censoring effect. To fill this gap, we present FreshRetailNet-50K, the first large-scale benchmark for censored demand estimation. It comprises 50,000 store-product time series of detailed hourly sales data from 898 stores in 18 major cities, encompassing 863 perishable SKUs meticulously annotated for stockout events. The hourly stock status records unique to this dataset, combined with rich contextual covariates, including promotional discounts, precipitation, and temporal features, enable innovative research beyond existing solutions. We demonstrate one such use case of two-stage demand modeling: first, we reconstruct the latent demand during stockouts using precise hourly annotations. We then leverage the recovered demand to train robust demand forecasting models in the second stage. Experimental results show that this approach achieves a 2.73% improvement in prediction accuracy while reducing the systematic demand underestimation from 7.37% to near-zero bias. With unprecedented temporal granularity and comprehensive real-world information, FreshRetailNet-50K opens new research directions in demand imputation, perishable inventory optimization, and causal retail analytics. The unique annotation quality and scale of the dataset address long-standing limitations in retail AI, providing immediate solutions and a platform for future methodological innovation. The data (https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K) and code (https://github.com/Dingdong-Inc/frn-50k-baseline}) are openly released.

Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on simple tasks. In this work, we systematically quantify the upper bounds of LRMs under both Long-Thinking and No-Thinking modes, and uncover the phenomenon of "Internal Self-Recovery Mechanism" where models implicitly supplement reasoning during answer generation. Building on this insight, we propose Adaptive Self-Recovery Reasoning (ASRR), a framework that suppresses unnecessary reasoning and enables implicit recovery. By introducing accuracy-aware length reward regulation, ASRR adaptively allocates reasoning effort according to problem difficulty, achieving high efficiency with negligible performance sacrifice. Experiments across multiple benchmarks and models show that, compared with GRPO, ASRR reduces reasoning budget by up to 32.5% (1.5B) and 25.7% (7B) with minimal accuracy loss (1.2% and 0.6% pass@1), and significantly boosts harmless rates on safety benchmarks (up to +21.7%). Our results highlight the potential of ASRR for enabling efficient, adaptive, and safer reasoning in LRMs.