Recent advancements in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. However, their reliability and trustworthiness are still in doubt, especially for concerns regarding individuals' data privacy. Great efforts have been made on privacy by building various evaluation benchmarks to study LLMs' privacy awareness and robustness from their generated outputs to their hidden representations. Unfortunately, most of these works adopt a narrow formulation of privacy and only investigate personally identifiable information (PII). In this paper, we follow the merit of the Contextual Integrity (CI) theory, which posits that privacy evaluation should not only cover the transmitted attributes but also encompass the whole relevant social context through private information flows. We present PrivaCI-Bench, a comprehensive contextual privacy evaluation benchmark targeted at legal compliance to cover well-annotated privacy and safety regulations, real court cases, privacy policies, and synthetic data built from the official toolkit to study LLMs' privacy and safety compliance. We evaluate the latest LLMs, including the recent reasoner models QwQ-32B and Deepseek R1. Our experimental results suggest that though LLMs can effectively capture key CI parameters inside a given context, they still require further advancements for privacy compliance.

As Large Language Models (LLMs) continue to advance in understanding and generating long sequences, new safety concerns have been introduced through the long context. However, the safety of LLMs in long-context tasks remains under-explored, leaving a significant gap in both evaluation and improvement of their safety. To address this, we introduce LongSafety, the first comprehensive benchmark specifically designed to evaluate LLM safety in open-ended long-context tasks. LongSafety encompasses 7 categories of safety issues and 6 user-oriented long-context tasks, with a total of 1,543 test cases, averaging 5,424 words per context. Our evaluation towards 16 representative LLMs reveals significant safety vulnerabilities, with most models achieving safety rates below 55%. Our findings also indicate that strong safety performance in short-context scenarios does not necessarily correlate with safety in long-context tasks, emphasizing the unique challenges and urgency of improving long-context safety. Moreover, through extensive analysis, we identify challenging safety issues and task types for long-context models. Furthermore, we find that relevant context and extended input sequences can exacerbate safety risks in long-context scenarios, highlighting the critical need for ongoing attention to long-context safety challenges. Our code and data are available at https://github.com/thu-coai/LongSafety.

Jailbreaking methods for large language models (LLMs) have gained increasing attention for building safe and responsible AI systems. After analyzing 35 jailbreak methods across six categories, we find that existing benchmarks, relying on universal LLM-based or keyword-matching scores, lack case-specific criteria, leading to conflicting results. In this paper, we introduce a more robust evaluation framework for jailbreak methods, with a curated harmful question dataset, detailed case-by-case evaluation guidelines, and a scoring system equipped with these guidelines. Our experiments show that existing jailbreak methods exhibit better discrimination when evaluated using our benchmark. Some jailbreak methods that claim to achieve over 90% attack success rate (ASR) on other benchmarks only reach a maximum of 30.2% on our benchmark, providing a higher ceiling for more advanced jailbreak research; furthermore, using our scoring system reduces the variance of disagreements between different evaluator LLMs by up to 76.33%. This demonstrates its ability to provide more fair and stable evaluation.

We first evaluate five LLMs' economic decision-making capabilities in solving two-period consumption allocation problems under two distinct scenarios: with explicit utility functions and based on intuitive reasoning. While previous research has often simulated heterogeneity by solely varying prompts, our approach harnesses the inherent variations in analytical capabilities across different LLMs to model agents with diverse cognitive traits. Building on these findings, we construct a Multi-LLM-Agent-Based (MLAB) framework by mapping these LLMs to specific educational groups and corresponding income brackets. Using interest-income taxation as a case study, we demonstrate how the MLAB framework can simulate policy impacts across heterogeneous agents, offering a promising new direction for economic and public policy analysis by leveraging LLMs' human-like reasoning capabilities and computational power.

The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be, unchecked AI agency poses significant risks to public safety and security, ranging from misuse by malicious actors to a potentially irreversible loss of human control. We discuss how these risks arise from current AI training methods. Indeed, various scenarios and experiments have demonstrated the possibility of AI agents engaging in deception or pursuing goals that were not specified by human operators and that conflict with human interests, such as self-preservation. Following the precautionary principle, we see a strong need for safer, yet still useful, alternatives to the current agency-driven trajectory. Accordingly, we propose as a core building block for further advances the development of a non-agentic AI system that is trustworthy and safe by design, which we call Scientist AI. This system is designed to explain the world from observations, as opposed to taking actions in it to imitate or please humans. It comprises a world model that generates theories to explain data and a question-answering inference machine. Both components operate with an explicit notion of uncertainty to mitigate the risks of overconfident predictions. In light of these considerations, a Scientist AI could be used to assist human researchers in accelerating scientific progress, including in AI safety. In particular, our system can be employed as a guardrail against AI agents that might be created despite the risks involved. Ultimately, focusing on non-agentic AI may enable the benefits of AI innovation while avoiding the risks associated with the current trajectory. We hope these arguments will motivate researchers, developers, and policymakers to favor this safer path.

The U.S. Securities and Exchange Commission (SEC) requires that public companies file financial reports tagging numbers with the machine readable inline eXtensible Business Reporting Language (iXBRL) standard. However, the highly complex and highly granular taxonomy defined by iXBRL limits label transferability across domains. In this paper, we introduce the Hierarchical Financial Key Performance Indicator (HiFi-KPI) dataset, designed to facilitate numerical KPI extraction at specified levels of granularity from unstructured financial text. Our approach organizes a 218,126-label hierarchy using a taxonomy based grouping method, investigating which taxonomy layer provides the most meaningful structure. HiFi-KPI comprises ~1.8M paragraphs and ~5M entities, each linked to a label in the iXBRL-specific calculation and presentation taxonomies. We provide baselines using encoder-based approaches and structured extraction using Large Language Models (LLMs). To simplify LLM inference and evaluation, we additionally release HiFi-KPI Lite, a manually curated subset with four expert-mapped labels. We publicly release all artifacts.

Large Language Models (LLMs) have emerged as transformative tools in artificial intelligence (AI), exhibiting remarkable capabilities across diverse tasks such as text generation, reasoning, and decision-making. While their success has primarily been driven by advances in computational power and deep learning architectures, emerging problems -- in areas such as uncertainty quantification, decision-making, causal inference, and distribution shift -- require a deeper engagement with the field of statistics. This paper explores potential areas where statisticians can make important contributions to the development of LLMs, particularly those that aim to engender trustworthiness and transparency for human users. Thus, we focus on issues such as uncertainty quantification, interpretability, fairness, privacy, watermarking and model adaptation. We also consider possible roles for LLMs in statistical analysis. By bridging AI and statistics, we aim to foster a deeper collaboration that advances both the theoretical foundations and practical applications of LLMs, ultimately shaping their role in addressing complex societal challenges.

Machine Unlearning (MU) aims at removing the influence of specific data points from a trained model, striving to achieve this at a fraction of the cost of full model retraining. In this paper, we analyze the efficiency of unlearning methods and establish the first upper and lower bounds on minimax computation times for this problem, characterizing the performance of the most efficient algorithm against the most difficult objective function. Specifically, for strongly convex objective functions and under the assumption that the forget data is inaccessible to the unlearning method, we provide a phase diagram for the unlearning complexity ratio -- a novel metric that compares the computational cost of the best unlearning method to full model retraining. The phase diagram reveals three distinct regimes: one where unlearning at a reduced cost is infeasible, another where unlearning is trivial because adding noise suffices, and a third where unlearning achieves significant computational advantages over retraining. These findings highlight the critical role of factors such as data dimensionality, the number of samples to forget, and privacy constraints in determining the practical feasibility of unlearning.

Principal Component Analysis (PCA) is a widely used method for dimensionality reduction, but it often overlooks fairness, especially when working with data that includes demographic characteristics. This can lead to biased representations that disproportionately affect certain groups. To address this issue, our approach incorporates Joint Eigenvalue Decomposition (JEVD), a technique that enables the simultaneous diagonalization of multiple matrices, ensuring both fair and efficient representations. We formally show that the optimal solution of JEVD leads to a fair PCA solution. By integrating JEVD with PCA, we strike an optimal balance between preserving data structure and promoting fairness across diverse groups. We demonstrate that our method outperforms existing baseline approaches in fairness and representational quality on various datasets. It retains the core advantages of PCA while ensuring that sensitive demographic attributes do not create disparities in the reduced representation.

More than 2,000 people, including leading creative names such as Mark Haddon, Axel Scheffler, Benji Davies and Michael Rosen, have signed a letter published in the Observer today calling on the government to keep the legal safeguards that offer artists and writers the prospect of a sustainable income. John predicted the proposal "would devastate our creative community", while helping "powerful foreign technology companies". The signatories say they understand the government aim of boosting growth, but describe themselves as "staring in astonishment" at Whitehall's eagerness "to hastily wrap our live's work in attractive paper as a welcome gift to automated competitors". "Imagine asking ChatGPT to generate your child's artwork instead of asking the child. It's a horrible thought, isn't it?" said children's book author and illustrator Ged Adamson.