Large Language Models (LLMs) have revolutionised natural language processing tasks, particularly as chat agents. However, their applicability to threat detection problems remains unclear. This paper examines the feasibility of employing LLMs as a Network Intrusion Detection System (NIDS), despite their high computational requirements, primarily for the sake of explainability. Furthermore, considerable resources have been invested in developing LLMs, and they may offer utility for NIDS. Current state-of-the-art NIDS rely on artificial benchmarking datasets, resulting in skewed performance when applied to real-world networking environments. Therefore, we compare the GPT-4 and LLama3 models against traditional architectures and transformer-based models to assess their ability to detect malicious NetFlows without depending on artificially skewed datasets, but solely on their vast pre-trained acquired knowledge. Our results reveal that, although LLMs struggle with precise attack detection, they hold significant potential for a path towards explainable NIDS. Our preliminary exploration shows that LLMs are unfit for the detection of Malicious NetFlows. Most promisingly, however, these exhibit significant potential as complementary agents in NIDS, particularly in providing explanations and aiding in threat response when integrated with Retrieval Augmented Generation (RAG) and function calling capabilities.

The advent of large language models has revolutionized natural language processing, but their increasing complexity has led to substantial training costs, resource demands, and environmental impacts. In response, sparse Mixture-of-Experts (MoE) models have emerged as a promising alternative to dense models. Since training MoE models from scratch can be prohibitively expensive, recent studies have explored leveraging knowledge from pre-trained non-MoE models. However, existing approaches have limitations, such as requiring significant hardware resources and data. We propose a novel algorithm, LaDiMo, which efficiently converts a Transformer-based non-MoE model into a MoE model with minimal additional training cost. LaDiMo consists of two stages: layer-wise expert construction and routing policy decision. By harnessing the concept of Knowledge Distillation, we compress the model and rapidly recover its performance. Furthermore, we develop an adaptive router that optimizes inference efficiency by profiling the distribution of routing weights and determining a layer-wise policy that balances accuracy and latency. We demonstrate the effectiveness of our method by converting the LLaMA2-7B model to a MoE model using only 100K tokens, reducing activated parameters by over 20% while keeping accuracy. Our approach offers a flexible and efficient solution for building and deploying MoE models.

Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges, which calls for comprehensive evaluation of tool-use capabilities. While previous works focused on either evaluating over stateless web services (RESTful API), based on a single turn user prompt, or an off-policy dialog trajectory, ToolSandbox includes stateful tool execution, implicit state dependencies between tools, a built-in user simulator supporting on-policy conversational evaluation and a dynamic evaluation strategy for intermediate and final milestones over an arbitrary trajectory. We show that open source and proprietary models have a significant performance gap, and complex tasks like State Dependency, Canonicalization and Insufficient Information defined in ToolSandbox are challenging even the most capable SOTA LLMs, providing brand-new insights into tool-use LLM capabilities. ToolSandbox evaluation framework is released at https://github.com/apple/ToolSandbox

But questions of Large language models (LLMs) have demonstrated human values and the answerability of the query generalization capabilities across NLP tasks such itself are difficult to model in terms of model confidence as question answering (QA) (Wei et al., 2022; (Yang et al., 2023). Chowdhery et al., 2022), abstractive summarization (Zhang et al., 2023a), and dialogue generation While prior work demonstrates the potential of (Yi et al., 2024). But these models are also unreliable, abstention in enhancing model safety and reliability having a tendency to "hallucinate" false information (Varshney et al., 2023; Wang et al., 2024c; in their responses (Ji et al., 2023b), generate Zhang et al., 2024a), the study of abstention has overly certain or authoritative responses (Zhou also been constrained to specific QA tasks. This et al., 2024b), answer with incomplete information task-specific approach limits the broader applicability (Zhou et al., 2023b), or produce harmful or of abstention strategies across the diverse dangerous responses (Anwar et al., 2024). In these range of scenarios encountered by general-purpose situations, the model should ideally abstain: to chatbots engaging in open-domain interactions.

Abstract: Powered by the emerging large language models (LLMs), autonomous geographic information systems (GIS) agents have the potential to accomplish spatial analyses and cartographic tasks. However, a research gap exists to support fully autonomous GIS agents: how to enable agents to discover and download the necessary data for geospatial analyses. This study proposes an autonomous GIS agent framework capable of retrieving required geospatial data by generating, executing, and debugging programs. The framework utilizes the LLM as the decision-maker, selects the appropriate data source (s) from a pre-defined source list, and fetches the data from the chosen source. Each data source has a handbook that records the metadata and technical details for data retrieval. The proposed framework is designed in a plug-and-play style to ensure flexibility and extensibility. Human users or autonomous data scrawlers can add new data sources by adding new handbooks. We developed a prototype agent based on the framework, released as a QGIS plugin (GeoData Retrieve Agent) and a Python program. Experiment results demonstrate its capability of retrieving data from various sources including OpenStreetMap, administrative boundaries and demographic data from the US Census Bureau, satellite basemaps from ESRI World Imagery, global digital elevation model (DEM) from OpenTopography.org, Our study is among the first attempts to develop an autonomous geospatial data retrieval agent. Keywords: autonomous GIS; geospatial data retrieval; large language models; generative AI; GIS agent; AI assistant 1 Introduction In recent years, large language models (LLMs) have drawn tremendous attention from researchers.

Significant research efforts have been made to scale and improve vision-language model (VLM) training approaches. Yet, with an ever-growing number of benchmarks, researchers are tasked with the heavy burden of implementing each protocol, bearing a non-trivial computational cost, and making sense of how all these benchmarks translate into meaningful axes of progress. To facilitate a systematic evaluation of VLM progress, we introduce UniBench: a unified implementation of 50+ VLM benchmarks spanning a comprehensive range of carefully categorized capabilities from object recognition to spatial awareness, counting, and much more. We showcase the utility of UniBench for measuring progress by evaluating nearly 60 publicly available vision-language models, trained on scales of up to 12.8B samples. We find that while scaling training data or model size can boost many vision-language model capabilities, scaling offers little benefit for reasoning or relations. Surprisingly, we also discover today's best VLMs struggle on simple digit recognition and counting tasks, e.g. MNIST, which much simpler networks can solve. Where scale falls short, we find that more precise interventions, such as data quality or tailored-learning objectives offer more promise. For practitioners, we also offer guidance on selecting a suitable VLM for a given application. Finally, we release an easy-to-run UniBench code-base with the full set of 50+ benchmarks and comparisons across 59 models as well as a distilled, representative set of benchmarks that runs in 5 minutes on a single GPU.

Can artificial intelligence be made to tell the truth? Probably not, but the developers of large language model (LLM) chatbots should be legally required to reduce the risk of errors, says a team of ethicists. "What we're just trying to do is create an incentive structure to get the companies to put a greater emphasis on truth or accuracy when they are creating the systems," says Brent Mittelstadt at the University of Oxford. How does ChatGPT work and do AI-powered chatbots "think" like us? LLM chatbots, such as ChatGPT, generate human-like responses to users' questions, based on statistical analysis of vast amounts of text. But although their answers usually appear convincing, they are also prone to errors – a flaw referred to as "hallucination".

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically difficult environment, is an under-explored topic. We conduct the first study to evaluate LLMs on a novel task of generating acoustically intelligible paraphrases for better human speech perception in noise. Our experiments in English demonstrated that with standard prompting, LLMs struggle to control the non-textual attribute, i.e., acoustic intelligibility, while efficiently capturing the desired textual attributes like semantic equivalence. To remedy this issue, we propose a simple prompting approach, prompt-and-select, which generates paraphrases by decoupling the desired textual and non-textual attributes in the text generation pipeline. Our approach resulted in a 40% relative improvement in human speech perception, by paraphrasing utterances that are highly distorted in a listening condition with babble noise at a signal-to-noise ratio (SNR) -5 dB. This study reveals the limitation of LLMs in capturing non-textual attributes, and our proposed method showcases the potential of using LLMs for better human speech perception in noise.

According to the World Health Organization (WHO), suicide was the fourth leading cause of death in the world for individuals aged 15 to 29 in 2019. Given the rapid increase in mental health issues, providing psychological support is both crucial and urgent. In this paper: (1) we propose S\'olo Esc\'uchame, the first open-source Spanish emotional assistance chatbot, based on LLaMA-2-7b-Chat. (2) We introduced the HEAR (Hispanic Emotional Accompaniment Responses) dataset, compiled from multiple English sources translated into Spanish, as well as generic data generated using ChatGPT-3.5-Turbo. Finally, (3) we propose an evaluation metric based on two semi-automatic assessment methods. Our system outperforms a range of state-of-the-art models in providing psychological assistance in Spanish. Our models and datasets are publicly available to facilitate reproducibility.

The recent trend in the Large Vision and Language model has brought a new change in how information extraction systems are built. VLMs have set a new benchmark with their State-of-the-art techniques in understanding documents and building question-answering systems across various industries. They are significantly better at generating text from document images and providing accurate answers to questions. However, there are still some challenges in effectively utilizing these models to build a precise conversational system. General prompting techniques used with large language models are often not suitable for these specially designed vision language models. The output generated by such generic input prompts is ordinary and may contain information gaps when compared with the actual content of the document. To obtain more accurate and specific answers, a well-targeted prompt is required by the vision language model, along with the document image. In this paper, a technique is discussed called Target prompting, which focuses on explicitly targeting parts of document images and generating related answers from those specific regions only. The paper also covers the evaluation of response for each prompting technique using different user queries and input prompts.