Low-resource languages face significant challenges due to the lack of sufficient linguistic data, resources, and tools for tasks such as supervised learning, annotation, and classification. This shortage hinders the development of accurate models and datasets, making it difficult to perform critical NLP tasks like sentiment analysis or hate speech detection. To bridge this gap, Large Language Models (LLMs) present an opportunity for potential annotators, capable of generating datasets and resources for these underrepresented languages. In this paper, we focus on Marathi, a low-resource language, and evaluate the performance of both closed-source and open-source LLMs as annotators. We assess models such as GPT-4o and Gemini 1.0 Pro, Gemma 2 (2B and 9B), and Llama 3.1 (8B) on classification tasks including sentiment analysis, news classification, and hate speech detection. Our findings reveal that while LLMs excel in annotation tasks for high-resource languages like English, they still fall short when applied to Marathi. Even advanced closed models like Gemini and GPT underperform in comparison to BERT-based baselines, highlighting the limitations of LLMs as annotators for low-resource languages.

Large Language Models (LLMs) have demonstrated remarkable planning abilities across various domains, including robotics manipulation and navigation. While recent efforts in robotics have leveraged LLMs both for high-level and low-level planning, these approaches often face significant challenges, such as hallucinations in long-horizon tasks and limited adaptability due to the generation of plans in a single pass without real-time feedback. To address these limitations, we propose a novel multi-agent LLM framework, Multi-Agent Large Language Model for Manipulation (MALMM) that distributes high-level planning and low-level control code generation across specialized LLM agents, supervised by an additional agent that dynamically manages transitions. By incorporating observations from the environment after each step, our framework effectively handles intermediate failures and enables adaptive re-planning. Unlike existing methods, our approach does not rely on pre-trained skill policies or in-context learning examples and generalizes to a variety of new tasks. We evaluate our approach on nine RLBench tasks, including long-horizon tasks, and demonstrate its ability to solve robotics manipulation in a zero-shot setting, thereby overcoming key limitations of existing LLM-based manipulation methods.

These authors contributed equally: J. Lee, J. Woo *: Corresponding author Corresponding author Email: Jihankim@kaist.ac.kr (Jihan Kim), stevepark@kaist.ac.kr (Steve Park), heetak.kim@kaist.ac.kr (Hee-Tak Kim) Abstract Recent advances in data-driven research have shown great potential in understanding the intricate relationships between materials and their performances. Herein, we introduce a novel multi modal data-driven approach employing an Automatic Battery data Collector (ABC) that integrates a large language model (LLM) with an automatic graph mining tool, Material Graph Digitizer (MatGD). This platform enables state-of-the-art accurate extraction of battery material data and cyclability performance metrics from diverse textual and graphical data sources. From the database derived through the ABC platform, we developed machine learning models that can accurately predict the capacity and stability of lithium metal batteries, which is the first-ever model developed to achieve such predictions. Our models were also experimentally validated, confirming practical applicability and reliability of our data-driven approach. INTRODUCTION Lithium metal batteries (LMBs) are a promising next-generation device that can achieve high capacity using lithium metal as an anode due to its exceptionally low density (0.534 g cm Therefore, these studies lack sufficient information to discern a comprehensive effect of different components on the battery performance. Additionally, previous mining research focused not on the entire battery cells but rather on the characteristics of individual battery components. Moreover, these studies were limited by the small number of entities considered and did not extract quantitative information such as concentrations or ratios. Furthermore, the absence of automatic graph mining tools made it difficult to obtain performance data from graphs, such as specific capacity and cycle stability.

Traditional archival practices for describing electronic theses and dissertations (ETDs) rely on broad, high-level metadata schemes that fail to capture the depth, complexity, and interdisciplinary nature of these long scholarly works. The lack of detailed, chapter-level content descriptions impedes researchers' ability to locate specific sections or themes, thereby reducing discoverability and overall accessibility. By providing chapter-level metadata information, we improve the effectiveness of ETDs as research resources. This makes it easier for scholars to navigate them efficiently and extract valuable insights. The absence of such metadata further obstructs interdisciplinary research by obscuring connections across fields, hindering new academic discoveries and collaboration. In this paper, we propose a machine learning and AI-driven solution to automatically categorize ETD chapters. This solution is intended to improve discoverability and promote understanding of chapters. Our approach enriches traditional archival practices by providing context-rich descriptions that facilitate targeted navigation and improved access. We aim to support interdisciplinary research and make ETDs more accessible. By providing chapter-level classification labels and using them to index in our developed prototype system, we make content in ETD chapters more discoverable and usable for a diverse range of scholarly needs. Implementing this AI-enhanced approach allows archives to serve researchers better, enabling efficient access to relevant information and supporting deeper engagement with ETDs. This will increase the impact of ETDs as research tools, foster interdisciplinary exploration, and reinforce the role of archives in scholarly communication within the data-intensive academic landscape.

The Virginia Tech University Libraries (VTUL) Digital Library Platform (DLP) hosts digital collections that offer our users access to a wide variety of documents of historical and cultural importance. These collections are not only of academic importance but also provide our users with a glance at local historical events. Our DLP contains collections comprising digital objects featuring complex layouts, faded imagery, and hard-to-read handwritten text, which makes providing online access to these materials challenging. To address these issues, we integrate AI into our DLP workflow and convert the text in the digital objects into a machine-readable format. To enhance the user experience with our historical collections, we use custom AI agents for handwriting recognition, text extraction, and large language models (LLMs) for summarization. This poster highlights three collections focusing on handwritten letters, newspapers, and digitized topographic maps. We discuss the challenges with each collection and detail our approaches to address them. Our proposed methods aim to enhance the user experience by making the contents in these collections easier to search and navigate.

As research institutions increasingly commit to supporting the United Nations' Sustainable Development Goals (SDGs), there is a pressing need to accurately assess their research output against these goals. Current approaches, primarily reliant on keyword-based Boolean search queries, conflate incidental keyword matches with genuine contributions, reducing retrieval precision and complicating benchmarking efforts. This study investigates the application of autoregressive Large Language Models (LLMs) as evaluation agents to identify relevant scholarly contributions to SDG targets in scholarly publications. Using a dataset of academic abstracts retrieved via SDG-specific keyword queries, we demonstrate that small, locally-hosted LLMs can differentiate semantically relevant contributions to SDG targets from documents retrieved due to incidental keyword matches, addressing the limitations of traditional methods. By leveraging the contextual understanding of LLMs, this approach provides a scalable framework for improving SDG-related research metrics and informing institutional reporting.

The increasing complexity and cost of clinical trials, particularly in the context of oncology and advanced therapies, pose significant challenges for drug development. This study evaluates the predictive capabilities of large language models (LLMs) such as GPT-3.5, GPT-4, and HINT in determining clinical trial outcomes. By leveraging a curated dataset of trials from ClinicalTrials.gov, we compare the models' performance using metrics including balanced accuracy, specificity, recall, and Matthews Correlation Coefficient (MCC). Results indicate that GPT-4o demonstrates robust performance in early trial phases, achieving high recall but facing limitations in specificity. Conversely, the HINT model excels in recognizing negative outcomes, particularly in later trial phases, offering a balanced approach across diverse endpoints. Oncology trials, characterized by high complexity, remain challenging for all models. Additionally, trial duration and disease categories influence predictive performance, with longer durations and complex diseases such as neoplasms reducing accuracy. This study highlights the complementary strengths of LLMs and HINT, providing insights into optimizing predictive tools for clinical trial design and risk management. Future advancements in LLMs are essential to address current gaps in handling negative outcomes and complex domains.

Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is to provide an overview of the development of VQA and a detailed description of the latest models with high timeliness. This survey gives an up-to-date synthesis of natural language understanding of images and text, as well as the knowledge reasoning module based on image-question information on the core VQA tasks. In addition, we elaborate on recent advances in extracting and fusing modal information with vision-language pretraining models and multimodal large language models in VQA. We also exhaustively review the progress of knowledge reasoning in VQA by detailing the extraction of internal knowledge and the introduction of external knowledge. Finally, we present the datasets of VQA and different evaluation metrics and discuss possible directions for future work.

This study explores the application of generative AI (GenAI) within manual exploitation and privilege escalation tasks in Linux-based penetration testing environments, two areas critical to comprehensive cybersecurity assessments. Building on previous research into the role of GenAI in the ethical hacking lifecycle, this paper presents a hands-on experimental analysis conducted in a controlled virtual setup to evaluate the utility of GenAI in supporting these crucial, often manual, tasks. Our findings demonstrate that GenAI can streamline processes, such as identifying potential attack vectors and parsing complex outputs for sensitive data during privilege escalation. The study also identifies key benefits and challenges associated with GenAI, including enhanced efficiency and scalability, alongside ethical concerns related to data privacy, unintended discovery of vulnerabilities, and potential for misuse. This work contributes to the growing field of AI-assisted cybersecurity by emphasising the importance of human-AI collaboration, especially in contexts requiring careful decision-making, rather than the complete replacement of human input.

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minimizing per-layer error, measured via various metrics. Yet, this approach currently lacks theoretical justification and the metrics employed may be sub-optimal. In this paper, we present a "linearity theorem" establishing a direct relationship between the layer-wise $\ell_2$ reconstruction error and the model perplexity increase due to quantization. This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, which outperforms all prior data-free approaches such as the extremely popular NF4 quantized format, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels which match a given compression constraint in the medium-bitwidth regime, obtained by reduction to dynamic programming. On the practical side, we demonstrate improved accuracy-compression trade-offs on Llama-3.1 and 3.2-family models, as well as on Qwen-family models. Further, we show that our method can be efficiently supported in terms of GPU kernels at various batch sizes, advancing both data-free and non-uniform quantization for LLMs.