Large language models (LLMs) have shown success in handling simple games with imperfect information and enabling multi-agent coordination, but their ability to facilitate practical collaboration against other agents in complex, imperfect information environments, especially in a non-English environment, still needs to be explored. This study investigates the applicability of knowledge acquired by open-source and API-based LLMs to sophisticated text-based games requiring agent collaboration under imperfect information, comparing their performance to established baselines using other types of agents. We propose a Theory of Mind (ToM) planning technique that allows LLM agents to adapt their strategy against various adversaries using only game rules, current state, and historical context as input. An external tool was incorporated to mitigate the challenge of dynamic and extensive action spaces in this card game. Our results show that although a performance gap exists between current LLMs and state-of-the-art reinforcement learning (RL) models, LLMs demonstrate ToM capabilities in this game setting. It consistently improves their performance against opposing agents, suggesting their ability to understand the actions of allies and adversaries and establish collaboration with allies. To encourage further research and understanding, we have made our codebase openly accessible.

Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional approaches for CMKD are based on a teacher/student paradigm where a teacher is trained on multi-modal data with the aim to successively distill knowledge from a multi-modal teacher to a single-modal student. Despite the widespread adoption of such paradigm, recent research has highlighted its inherent limitations in the context of cross-modal knowledge transfer.Taking a step beyond the teacher/student paradigm, here we introduce a new framework for cross-modal knowledge distillation, named DisCoM-KD (Disentanglement-learning based Cross-Modal Knowledge Distillation), that explicitly models different types of per-modality information with the aim to transfer knowledge from multi-modal data to a single-modal classifier. To this end, DisCoM-KD effectively combines disentanglement representation learning with adversarial domain adaptation to simultaneously extract, foreach modality, domain-invariant, domain-informative and domain-irrelevant features according to a specific downstream task. Unlike the traditional teacher/student paradigm, our framework simultaneously learns all single-modal classifiers, eliminating the need to learn each student model separately as well as the teacher classifier. We evaluated DisCoM-KD on three standard multi-modal benchmarks and compared its behaviourwith recent SOTA knowledge distillation frameworks. The findings clearly demonstrate the effectiveness of DisCoM-KD over competitors considering mismatch scenarios involving both overlapping and non-overlapping modalities. These results offer insights to reconsider the traditional paradigm for distilling information from multi-modal data to single-modal neural networks.

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to automatically generate adversarial prompts for red teaming. However, the evolving subtlety of vulnerabilities in LLMs challenges the effectiveness of current adversarial methods, which struggle to specifically target and explore the weaknesses of these models. To tackle these challenges, we introduce the $\mathbf{S}\text{elf-}\mathbf{E}\text{volving }\mathbf{A}\text{dversarial }\mathbf{S}\text{afety }\mathbf{(SEAS)}$ optimization framework, which enhances security by leveraging data generated by the model itself. SEAS operates through three iterative stages: Initialization, Attack, and Adversarial Optimization, refining both the Red Team and Target models to improve robustness and safety. This framework reduces reliance on manual testing and significantly enhances the security capabilities of LLMs. Our contributions include a novel adversarial framework, a comprehensive safety dataset, and after three iterations, the Target model achieves a security level comparable to GPT-4, while the Red Team model shows a marked increase in attack success rate (ASR) against advanced models.

Feature grid Scene Representation Networks (SRNs) have been applied to scientific data as compact functional surrogates for analysis and visualization. As SRNs are black-box lossy data representations, assessing the prediction quality is critical for scientific visualization applications to ensure that scientists can trust the information being visualized. Currently, existing architectures do not support inference time reconstruction quality assessment, as coordinate-level errors cannot be evaluated in the absence of ground truth data. We propose a parameter-efficient multi-decoder SRN (MDSRN) ensemble architecture consisting of a shared feature grid with multiple lightweight multi-layer perceptron decoders. MDSRN can generate a set of plausible predictions for a given input coordinate to compute the mean as the prediction of the multi-decoder ensemble and the variance as a confidence score. The coordinate-level variance can be rendered along with the data to inform the reconstruction quality, or be integrated into uncertainty-aware volume visualization algorithms. To prevent the misalignment between the quantified variance and the prediction quality, we propose a novel variance regularization loss for ensemble learning that promotes the Regularized multi-decoder SRN (RMDSRN) to obtain a more reliable variance that correlates closely to the true model error. We comprehensively evaluate the quality of variance quantification and data reconstruction of Monte Carlo Dropout, Mean Field Variational Inference, Deep Ensemble, and Predicting Variance compared to the proposed MDSRN and RMDSRN across diverse scalar field datasets. We demonstrate that RMDSRN attains the most accurate data reconstruction and competitive variance-error correlation among uncertain SRNs under the same neural network parameter budgets.

The independence assumption is a useful tool to increase the tractability of one's modelling framework. However, this assumption does not match reality; failing to take dependencies into account can cause models to fail dramatically. The field of multi-axis graphical modelling (also called multi-way modelling, Kronecker-separable modelling) has seen growth over the past decade, but these models require that the data have zero mean. In the multi-axis case, inference is typically done in the single sample scenario, making mean inference impossible. In this paper, we demonstrate how the zero-mean assumption can cause egregious modelling errors, as well as propose a relaxation to the zero-mean assumption that allows the avoidance of such errors. Specifically, we propose the "Kronecker-sum-structured mean" assumption, which leads to models with nonconvex-but-unimodal log-likelihoods that can be solved efficiently with coordinate descent.

Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and safety benchmarks in response. However, existing public benchmarks often define safety categories based on previous literature, intuitions, or common sense, leading to disjointed sets of categories for risks specified in recent regulations and policies, which makes it challenging to evaluate and compare FMs across these benchmarks. To bridge this gap, we introduce AIR-Bench 2024, the first AI safety benchmark aligned with emerging government regulations and company policies, following the regulation-based safety categories grounded in our AI risks study, AIR 2024. AIR 2024 decomposes 8 government regulations and 16 company policies into a four-tiered safety taxonomy with 314 granular risk categories in the lowest tier. AIR-Bench 2024 contains 5,694 diverse prompts spanning these categories, with manual curation and human auditing to ensure quality. We evaluate leading language models on AIR-Bench 2024, uncovering insights into their alignment with specified safety concerns. By bridging the gap between public benchmarks and practical AI risks, AIR-Bench 2024 provides a foundation for assessing model safety across jurisdictions, fostering the development of safer and more responsible AI systems.

The senses of words evolve. The sense of the same word may change from today to tomorrow, and multiple senses of the same word may be the result of the evolution of each other, that is, they may be parents and children. If we view Juba as an evolving ecosystem, the paradigm of learning the correct answer, which does not move with the sense of a word, is no longer valid. This paper is a case study that shows that word polysemy is an evolutionary consequence of the modification of Semantic Cells, which has al-ready been presented by the author, by introducing a small amount of diversity in its initial state as an example of analyzing the current set of short sentences. In particular, the analysis of a sentence sequence of 1000 sentences in some order for each of the four senses of the word Spring, collected using Chat GPT, shows that the word acquires the most polysemy monotonically in the analysis when the senses are arranged in the order in which they have evolved. In other words, we present a method for analyzing the dynamism of a word's acquiring polysemy with evolution and, at the same time, a methodology for viewing polysemy from an evolutionary framework rather than a learning-based one.

It has now been close to 10 months that Israel has been waging a genocidal war in Gaza. Its army has violated nearly every facet of international humanitarian law in its relentless assault on an unimaginably vulnerable population. Israel has denied the Gaza concentration camp the bare necessities of life -- food, water, medicine, sanitation, electricity and fuel. And its targeting of civilian infrastructure has made the majority of Gaza residents homeless. No Israeli military goal requires the total destruction of Gaza.

Calls to use open generative language models in academic research have highlighted the need for reproducibility and transparency in scientific research. However, the impact of generative AI extends well beyond academia, as corporations and public interest organizations have begun integrating these models into their data science pipelines. We expand this lens to include the impact of open models on organizations, focusing specifically on fact-checking organizations, which use AI to observe and analyze large volumes of circulating misinformation, yet must also ensure the reproducibility and impartiality of their work. We wanted to understand where fact-checking organizations use open models in their data science pipelines; what motivates their use of open models or proprietary models; and how their use of open or proprietary models can inform research on the societal impact of generative AI. To answer these questions, we conducted an interview study with N=24 professionals at 20 fact-checking organizations on six continents. Based on these interviews, we offer a five-component conceptual model of where fact-checking organizations employ generative AI to support or automate parts of their data science pipeline, including Data Ingestion, Data Analysis, Data Retrieval, Data Delivery, and Data Sharing. We then provide taxonomies of fact-checking organizations' motivations for using open models and the limitations that prevent them for further adopting open models, finding that they prefer open models for Organizational Autonomy, Data Privacy and Ownership, Application Specificity, and Capability Transparency. However, they nonetheless use proprietary models due to perceived advantages in Performance, Usability, and Safety, as well as Opportunity Costs related to participation in emerging generative AI ecosystems. Our work provides novel perspective on open models in data-driven organizations.

The rapid advancement and widespread deployment of foundation model (FM) based systems have revolutionized numerous applications across various domains. However, the fast-growing capabilities and autonomy have also raised significant concerns about responsible AI and AI safety. Recently, there have been increasing attention toward implementing guardrails to ensure the runtime behavior of FM-based systems is safe and responsible. Given the early stage of FMs and their applications (such as agents), the design of guardrails have not yet been systematically studied. It remains underexplored which software qualities should be considered when designing guardrails and how these qualities can be ensured from a software architecture perspective. Therefore, in this paper, we present a taxonomy for guardrails to classify and compare the characteristics and design options of guardrails. Our taxonomy is organized into three main categories: the motivation behind adopting runtime guardrails, the quality attributes to consider, and the design options available. This taxonomy provides structured and concrete guidance for making architectural design decisions when designing guardrails and highlights trade-offs arising from the design decisions.