Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it has offered limited explanatory and predictive power for general-purpose AI systems, given the low transferability across diverse tasks. In this paper, we introduce general scales for AI evaluation that can explain what common AI benchmarks really measure, extract ability profiles of AI systems, and predict their performance for new task instances, in- and out-of-distribution. Our fully-automated methodology builds on 18 newly-crafted rubrics that place instance demands on general scales that do not saturate. Illustrated for 15 large language models and 63 tasks, high explanatory power is unleashed from inspecting the demand and ability profiles, bringing insights on the sensitivity and specificity exhibited by different benchmarks, and how knowledge, metacognition and reasoning are affected by model size, chain-of-thought and distillation. Surprisingly, high predictive power at the instance level becomes possible using these demand levels, providing superior estimates over black-box baseline predictors based on embeddings or finetuning, especially in out-of-distribution settings (new tasks and new benchmarks). The scales, rubrics, battery, techniques and results presented here represent a major step for AI evaluation, underpinning the reliable deployment of AI in the years ahead. (Collaborative platform: https://kinds-of-intelligence-cfi.github.io/ADELE.)

The recent leap in AI capabilities, driven by big generative models, has sparked the possibility of achieving Artificial General Intelligence (AGI) and further triggered discussions on Artificial Superintelligence (ASI), a system surpassing all humans across all domains. This gives rise to the critical research question of: If we realize ASI, how do we align it with human values, ensuring it benefits rather than harms human society, a.k.a., the Superalignment problem. Despite ASI being regarded by many as solely a hypothetical concept, in this paper, we argue that superalignment is achievable and research on it should advance immediately, through simultaneous and alternating optimization of task competence and value conformity. We posit that superalignment is not merely a safeguard for ASI but also necessary for its realization. To support this position, we first provide a formal definition of superalignment rooted in the gap between capability and capacity and elaborate on our argument. Then we review existing paradigms, explore their interconnections and limitations, and illustrate a potential path to superalignment centered on two fundamental principles. We hope this work sheds light on a practical approach for developing the value-aligned next-generation AI, garnering greater benefits and reducing potential harms for humanity.

Existing research has primarily focused on static analyses that assess the disparities in the existing knowledge and capabilities of LLMs across languages. However, LLMs are continuously evolving, acquiring new knowledge to generate up-to-date, domain-specific responses. Investigating linguistic inequalities within this dynamic process is, therefore, also essential. In this paper, we explore inequalities in new knowledge learning by LLMs across different languages and four key dimensions: effectiveness, transferability, prioritization, and robustness. Through extensive experiments under two settings (in-context learning and fine-tuning) using both proprietary and open-source models, we demonstrate that low-resource languages consistently face disadvantages across all four dimensions. By shedding light on these disparities, we aim to raise awareness of linguistic inequities in LLMs' new knowledge learning, fostering the development of more inclusive and equitable future LLMs. This transformation is both inevitable and global in scale. One notable example is ChatGPT, which, as of December 2024, serves 300 million weekly active users worldwide (6, 7). Given such widespread adoption, it is crucial to study fairness in multilingual environments to ensure that users of different languages can benefit equally from these systems (9). Existing research on multilingual equality in LLMs primarily focuses on static analyses that evaluate disparities in the knowledge and capabilities of LLMs across different languages (10, 11, 12, 13, 14, 15, 16, 17). Some studies, for example, have examined the amount of factual knowledge encoded in different languages and revealed significant variations. In particular, they reveal that knowledge available in low-resource languages remains limited due to the lack of pre-training data in these languages (18, 19, 20). These studies have significantly advanced our understanding of the extent and nature of multilingual inequalities in LLMs' existing knowledge and capabilities. However, we still lack an understanding of inequalities in the process of acquiring new knowledge, an evolving perspective in research on LLMs. Learning new knowledge is crucial for LLMs, as illustrated in Figure 1a. On the one hand, general-purpose LLMs are pre-trained on static datasets that were collected prior to training and may not include real-time or recent information. As a result, these models do not possess new knowledge, and their knowledge base can quickly become outdated.

Intelligent Tutoring Systems (ITSs) have revolutionized education by offering personalized learning experiences. However, as goal-oriented learning, which emphasizes efficiently achieving specific objectives, becomes increasingly important in professional contexts, existing ITSs often struggle to deliver this type of targeted learning experience. In this paper, we propose GenMentor, an LLM-powered multi-agent framework designed to deliver goal-oriented, personalized learning within ITS. GenMentor begins by accurately mapping learners' goals to required skills using a fine-tuned LLM trained on a custom goal-to-skill dataset. After identifying the skill gap, it schedules an efficient learning path using an evolving optimization approach, driven by a comprehensive and dynamic profile of learners' multifaceted status. Additionally, GenMentor tailors learning content with an exploration-drafting-integration mechanism to align with individual learner needs. Extensive automated and human evaluations demonstrate GenMentor's effectiveness in learning guidance and content quality. Furthermore, we have deployed it in practice and also implemented it as an application. Practical human study with professional learners further highlights its effectiveness in goal alignment and resource targeting, leading to enhanced personalization. Supplementary resources are available at https://github.com/GeminiLight/gen-mentor.

As Large Language Models (LLMs) achieve remarkable breakthroughs, aligning their values with humans has become imperative for their responsible development and customized applications. However, there still lack evaluations of LLMs values that fulfill three desirable goals. (1) Value Clarification: We expect to clarify the underlying values of LLMs precisely and comprehensively, while current evaluations focus narrowly on safety risks such as bias and toxicity. (2) Evaluation Validity: Existing static, open-source benchmarks are prone to data contamination and quickly become obsolete as LLMs evolve. Additionally, these discriminative evaluations uncover LLMs' knowledge about values, rather than valid assessments of LLMs' behavioral conformity to values. (3) Value Pluralism: The pluralistic nature of human values across individuals and cultures is largely ignored in measuring LLMs value alignment. To address these challenges, we presents the Value Compass Leaderboard, with three correspondingly designed modules. It (i) grounds the evaluation on motivationally distinct \textit{basic values to clarify LLMs' underlying values from a holistic view; (ii) applies a \textit{generative evolving evaluation framework with adaptive test items for evolving LLMs and direct value recognition from behaviors in realistic scenarios; (iii) propose a metric that quantifies LLMs alignment with a specific value as a weighted sum over multiple dimensions, with weights determined by pluralistic values.

Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding, often misinterpreting symbols, gestures, and artifacts due to biases in predominantly Western-centric training data. In this paper, we construct CultureVerse, a large-scale multimodal benchmark covering 19, 682 cultural concepts, 188 countries/regions, 15 cultural concepts, and 3 question types, with the aim of characterizing and improving VLMs' multicultural understanding capabilities. Then, we propose CultureVLM, a series of VLMs fine-tuned on our dataset to achieve significant performance improvement in cultural understanding. Our evaluation of 16 models reveals significant disparities, with a stronger performance in Western concepts and weaker results in African and Asian contexts. Fine-tuning on our CultureVerse enhances cultural perception, demonstrating cross-cultural, cross-continent, and cross-dataset generalization without sacrificing performance on models' general VLM benchmarks. We further present insights on cultural generalization and forgetting. We hope that this work could lay the foundation for more equitable and culturally aware multimodal AI systems.

The emergence of large language models (LLMs) has sparkedthe discussion on Artificial Superintelligence (ASI), a hypothetical AI system surpassing human intelligence. Though ASI is still hypothetical and far from current AI capabilities, existing alignment methods struggle to guide such advanced AI ensure its safety in the future. It is essential to discuss the alignment of such AI now. Superalignment, the alignment of AI at superhuman levels of capability systems with human values and safety requirements, aims to address two primary goals: scalability in supervision to provide high-quality guidance signals and robust governance to ensure alignment with human values. In this survey, we review the original scalable oversight problem and corresponding methods and potential solutions for superalignment. Specifically, we introduce the Figure 1: Challenges from the perspectives of supervision challenges and limitations of current alignment and governance. While supervision perspective paradigms in addressing the superalignment focuses on providing high-quality guidance signals for problem. Then we review scalable oversight enhancing system competence, governance perspective methods for superalignment. Finally, we discuss emphasizes aligning the behavior of advanced aI with the key challenges and propose pathways human values to prevent harmful outcomes.

Despite the recent advancement of Large Langauge Models (LLMs), they struggle with complex queries often involving multiple conditions, common in real-world scenarios. We propose Thinking with Tables, a technique that assists LLMs to leverage tables for intermediate thinking aligning with human cognitive behavior. By introducing a pre-instruction that triggers an LLM to organize information in tables, our approach achieves a 40.29\% average relative performance increase, higher robustness, and show generalizability to different requests, conditions, or scenarios. We additionally show the influence of data structuredness for the model by comparing results from four distinct structuring levels that we introduce.

Trending topics have become a significant part of modern social media, attracting users to participate in discussions of breaking events. However, they also bring in a new channel for poisoning attacks, resulting in negative impacts on society. Therefore, it is urgent to study this critical problem and develop effective strategies for defense. In this paper, we propose TrendSim, an LLM-based multi-agent system to simulate trending topics in social media under poisoning attacks. Specifically, we create a simulation environment for trending topics that incorporates a time-aware interaction mechanism, centralized message dissemination, and an interactive system. Moreover, we develop LLM-based human-like agents to simulate users in social media, and propose prototype-based attackers to replicate poisoning attacks. Besides, we evaluate TrendSim from multiple aspects to validate its effectiveness. Based on TrendSim, we conduct simulation experiments to study four critical problems about poisoning attacks on trending topics for social benefit.

Role-playing is a crucial capability of Large Language Models (LLMs), enabling a wide range of practical applications, including intelligent non-player characters, digital twins, and emotional companions. Evaluating this capability in LLMs is challenging due to the complex dynamics involved in role-playing, such as maintaining character fidelity throughout a storyline and navigating open-ended narratives without a definitive ground truth. Current evaluation methods, which primarily focus on question-answering or conversational snapshots, fall short of adequately capturing the nuanced character traits and behaviors essential for authentic role-playing. In this paper, we propose CharacterBox, which is a simulation sandbox designed to generate situational fine-grained character behavior trajectories. These behavior trajectories enable a more comprehensive and in-depth evaluation of role-playing capabilities. CharacterBox consists of two main components: the character agent and the narrator agent. The character agent, grounded in psychological and behavioral science, exhibits human-like behaviors, while the narrator agent coordinates interactions between character agents and environmental changes. Additionally, we introduce two trajectory-based methods that leverage CharacterBox to enhance LLM performance. To reduce costs and facilitate the adoption of CharacterBox by public communities, we fine-tune two smaller models, CharacterNR and CharacterRM, as substitutes for GPT API calls, and demonstrate their competitive performance compared to advanced GPT APIs.