The dataset contains 1003 multiple-choice questions in Spanish from various With the recent progress in broadening the generalisation subjects of the UNED Access Course for Over-25s capabilities of Large Language Models in Spanish, and high-quality English professional (LLMs), much current research focuses on understanding translations. Two characteristics make this dataset their capabilities and limitations. Evaluations unique: first, the contamination level should be of the most recent generative models, such minimal because UNED typically does not release as Llama-2 (Touvron et al., 2023b), Mistral (Jiang the answers to the exam questions, which are only et al., 2023), Mixtral (Jiang et al., 2024a), Gemini accessible to the teachers of each course. Second, (Anil et al., 2024), Gemma (Mesnard et al., this is a high-quality bilingual dataset, with original 2024), GPT-3.5 (Brown et al., 2020), GPT-4 and questions in Spanish translated into English GPT-4o (Achiam et al., 2024), attempt at measuring manually by a professional translators who did not their world knowledge, memorisation and inference use any external software.

Developing novel interdisciplinary research ideas often requires discussions and feedback from experts across different domains. However, obtaining timely inputs is challenging due to the scarce availability of domain experts. Recent advances in Large Language Model (LLM) research have suggested the feasibility of utilizing LLM-simulated expert personas to support research ideation. In this study, we introduce PersonaFlow, an LLM-based system using persona simulation to support the ideation stage of interdisciplinary scientific discovery. Our findings indicate that using multiple personas during ideation significantly enhances user-perceived quality of outcomes (e.g., relevance of critiques, creativity of research questions) without increasing cognitive load. We also found that users' persona customization interactions significantly improved their sense of control and recall of generated ideas. Based on the findings, we discuss highlighting ethical concerns, including potential over-reliance and cognitive biases, and suggest design implications for leveraging LLM-simulated expert personas to support research ideation when human expertise is inaccessible.

In this work, we significantly enhance masked particle modeling (MPM), a self-supervised learning scheme for constructing highly expressive representations of unordered sets relevant to developing foundation models for high-energy physics. In MPM, a model is trained to recover the missing elements of a set, a learning objective that requires no labels and can be applied directly to experimental data. We achieve significant performance improvements over previous work on MPM by addressing inefficiencies in the implementation and incorporating a more powerful decoder. We compare several pre-training tasks and introduce new reconstruction methods that utilize conditional generative models without data tokenization or discretization. We show that these new methods outperform the tokenized learning objective from the original MPM on a new test bed for foundation models for jets, which includes using a wide variety of downstream tasks relevant to jet physics, such as classification, secondary vertex finding, and track identification.

Recent advancements in large language and vision-language models have significantly enhanced multimodal understanding, yet translating high-level linguistic instructions into precise robotic actions in 3D space remains challenging. This paper introduces IRIS (Interactive Responsive Intelligent Segmentation), a novel training-free multimodal system for 3D affordance segmentation, alongside a benchmark for evaluating interactive language-guided affordance in everyday environments. IRIS integrates a large multimodal model with a specialized 3D vision network, enabling seamless fusion of 2D and 3D visual understanding with language comprehension. To facilitate evaluation, we present a dataset of 10 typical indoor environments, each with 50 images annotated for object actions and 3D affordance segmentation. Extensive experiments demonstrate IRIS's capability in handling interactive 3D affordance segmentation tasks across diverse settings, showcasing competitive performance across various metrics. Our results highlight IRIS's potential for enhancing human-robot interaction based on affordance understanding in complex indoor environments, advancing the development of more intuitive and efficient robotic systems for real-world applications.

To explore how we can gain deeper insights on this topic, we performed a network analysis on a comprehensive knowledge graph (KG) of ADHD, constructed by integrating scientific literature and clinical data with the help of cutting-edge large language models. The analysis, including k-core techniques, identified critical nodes and relationships that are central to understanding the disorder. Building on these findings, we developed a context-aware chatbot using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), enabling accurate and informed interactions. Our knowledge graph not only advances the understanding of ADHD but also provides a powerful tool for research and clinical applications.

The development of Multimodal Large Language Models (MLLMs) has seen significant advancements with increasing demands in various fields (e.g., multimodal agents, embodied intelligence). While model-driven approaches attempt to enhance MLLMs capabilities through diverse architectures, the gains have become increasingly marginal. Conversely, data-driven methods, which scale up image-text instruction data, are more effective but face limited data diversity and complexity challenges. The absence of high-quality data constitutes a significant development barrier for MLLMs. To address the data quality bottleneck, we propose MMEvol, a novel multimodal instruction data evolution framework. This framework iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities. Beginning with an initial set of instructions, SEED-163K, we utilize MMEvol to systematically broaden the diversity of instruction types, extend visual reasoning steps to improve cognitive reasoning abilities, and thoroughly explore fine-grained information within images to enhance visual understanding and robustness. To comprehensively evaluate the effectiveness of our approach, we conduct extensive qualitative analysis and quantitative experiments across 13 vision-language tasks. Compared to baseline models trained with the initial seed data, the results demonstrate that our method achieves an average accuracy improvement of 3.1 percentage points. Furthermore, our approach reaches state-of-the-art (SOTA) performance in nine tasks using significantly less data compared to state-of-the-art models.

There has been a surge of interest in language model agents that can navigate virtual environments such as the web or desktop. To navigate such environments, agents benefit from information on the various elements (e.g., buttons, text, or images) present. It remains unclear which element attributes have the greatest impact on agent performance, especially in environments that only provide a graphical representation (i.e., pixels). Here we find that the ordering in which elements are presented to the language model is surprisingly impactful--randomizing element ordering in a webpage degrades agent performance comparably to removing all visible text from an agent's state representation. While a webpage provides a hierarchical ordering of elements, there is no such ordering when parsing elements directly from pixels. Moreover, as tasks become more challenging and models more sophisticated, our experiments suggest that the impact of ordering increases. Finding an effective ordering is non-trivial. We investigate the impact of various element ordering methods in web and desktop environments. We find that dimensionality reduction provides a viable ordering for pixel-only environments. We train a UI element detection model to derive elements from pixels and apply our findings to an agent benchmark--OmniACT--where we only have access to pixels. Our method completes more than two times as many tasks on average relative to the previous state-of-the-art.

The Automated Audio Captioning (AAC) task asks models to generate natural language descriptions of an audio input. Evaluating these machine-generated audio captions is a complex task that requires considering diverse factors, among them, auditory scene understanding, sound-object inference, temporal coherence, and the environmental context of the scene. While current methods focus on specific aspects, they often fail to provide an overall score that aligns well with human judgment. In this work, we propose CLAIR-A, a simple and flexible method that leverages the zero-shot capabilities of large language models (LLMs) to evaluate candidate audio captions by directly asking LLMs for a semantic distance score. In our evaluations, CLAIR-A better predicts human judgements of quality compared to traditional metrics, with a 5.8% relative accuracy improvement compared to the domain-specific FENSE metric and up to 11% over the best general-purpose measure on the Clotho-Eval dataset. Moreover, CLAIR-A offers more transparency by allowing the language model to explain the reasoning behind its scores, with these explanations rated up to 30% better by human evaluators than those provided by baseline methods. CLAIR-A is made publicly available at https://github.com/DavidMChan/clair-a.

Large Language Models (LLMs) have shown significant promise in plan generation. Yet, existing datasets often lack the complexity needed for advanced tool use scenarios -- such as handling paraphrased query statements, supporting multiple languages, and managing actions that can be done in parallel. These scenarios are crucial for evaluating the evolving capabilities of LLMs in real-world applications. Moreover, current datasets don't enable the study of LLMs from a process perspective, particularly in scenarios where understanding typical behaviors and challenges in executing the same process under different conditions or formulations is crucial. To address these gaps, we present the ProcessTBench synthetic dataset, an extension of the TaskBench dataset specifically designed to evaluate LLMs within a process mining framework.

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety-aligned LLMs are known to be vulnerable to training-time attacks such as supervised fine-tuning (SFT) on harmful datasets. In this paper, we ask if LLMs are vulnerable to adversarial reinforcement learning. Motivated by this goal, we propose Reverse Preference Attacks (RPA), a class of attacks to make LLMs learn harmful behavior using adversarial reward during reinforcement learning from human feedback (RLHF). RPAs expose a critical safety gap of safety-aligned LLMs in RL settings: they easily explore the harmful text generation policies to optimize adversarial reward. To protect against RPAs, we explore a host of mitigation strategies. Leveraging Constrained Markov-Decision Processes, we adapt a number of mechanisms to defend against harmful fine-tuning attacks into the RL setting. Our experiments show that ``online" defenses that are based on the idea of minimizing the negative log likelihood of refusals -- with the defender having control of the loss function -- can effectively protect LLMs against RPAs. However, trying to defend model weights using ``offline" defenses that operate under the assumption that the defender has no control over the loss function are less effective in the face of RPAs. These findings show that attacks done using RL can be used to successfully undo safety alignment in open-weight LLMs and use them for malicious purposes.