Warning: This paper may contain texts with uncomfortable content. Large Language Models (LLMs) have achieved remarkable performance in various tasks, including those involving multimodal data like speech. However, these models often exhibit biases due to the nature of their training data. Recently, more Speech Large Language Models (SLLMs) have emerged, underscoring the urgent need to address these biases. This study introduces Spoken Stereoset, a dataset specifically designed to evaluate social biases in SLLMs. By examining how different models respond to speech from diverse demographic groups, we aim to identify these biases. Our experiments reveal significant insights into their performance and bias levels. The findings indicate that while most models show minimal bias, some still exhibit slightly stereotypical or anti-stereotypical tendencies.

The rise of Large Language Models (LLMs) has impacted research in robotics and automation. While progress has been made in integrating LLMs into general robotics tasks, a noticeable void persists in their adoption in more specific domains such as surgery, where critical factors such as reasoning, explainability, and safety are paramount. Achieving autonomy in robotic surgery, which entails the ability to reason and adapt to changes in the environment, remains a significant challenge. In this work, we propose a multi-modal LLM integration in robot-assisted surgery for autonomous blood suction. The reasoning and prioritization are delegated to the higher-level task-planning LLM, and the motion planning and execution are handled by the lower-level deep reinforcement learning model, creating a distributed agency between the two components. As surgical operations are highly dynamic and may encounter unforeseen circumstances, blood clots and active bleeding were introduced to influence decision-making. Results showed that using a multi-modal LLM as a higher-level reasoning unit can account for these surgical complexities to achieve a level of reasoning previously unattainable in robot-assisted surgeries. These findings demonstrate the potential of multi-modal LLMs to significantly enhance contextual understanding and decision-making in robotic-assisted surgeries, marking a step toward autonomous surgical systems.

While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come in many forms, and there is no universally accepted definition. We thus focus on studying only those hallucinations where a correct answer appears verbatim in the training set. To fully control the training data content, we construct a knowledge graph (KG)-based dataset, and use it to train a set of increasingly large LMs. We find that for a fixed dataset, larger and longer-trained LMs hallucinate less. However, hallucinating on $\leq5$% of the training data requires an order of magnitude larger model, and thus an order of magnitude more compute, than Hoffmann et al. (2022) reported was optimal. Given this costliness, we study how hallucination detectors depend on scale. While we see detector size improves performance on fixed LM's outputs, we find an inverse relationship between the scale of the LM and the detectability of its hallucinations.

Others have invented alternative sequence mixing architectures such as state-space models which are designed The self-attention operation is the core computational to be efficiently computable in linear time and constant building block of the transformer architecture [1, 2], memory [25-29]. Other approaches utilize efficient algorithms which has become an ubiquitous and highly effective to reduce the computational burden of attention workhorse architecture currently applied at scale to language while keeping the core computation the same. These include [3-7], vision [8], audio [9], and decision-making memory-efficient attention [30], Flash Attention [10, 11]. Nonetheless, the quadratic time complexity of [31] and Flash Decoding [32], which provide a set of IOaware self-attention means that significant resources are required kernels to map the attention operation to the GPU to train and generate from transformer-based Large Language hardware resources in an extremely efficient way, significantly Models (LLMs), especially for models with large reducing the memory overhead required.

Data visualization (DV) is the fundamental and premise tool to improve the efficiency in conveying the insights behind the big data, which has been widely accepted in existing data-driven world. Task automation in DV, such as converting natural language queries to visualizations (i.e., text-to-vis), generating explanations from visualizations (i.e., vis-to-text), answering DV-related questions in free form (i.e. FeVisQA), and explicating tabular data (i.e., table-to-text), is vital for advancing the field. Despite their potential, the application of pre-trained language models (PLMs) like T5 and BERT in DV has been limited by high costs and challenges in handling cross-modal information, leading to few studies on PLMs for DV. We introduce \textbf{DataVisT5}, a novel PLM tailored for DV that enhances the T5 architecture through a hybrid objective pre-training and multi-task fine-tuning strategy, integrating text and DV datasets to effectively interpret cross-modal semantics. Extensive evaluations on public datasets show that DataVisT5 consistently outperforms current state-of-the-art models on various DV-related tasks. We anticipate that DataVisT5 will not only inspire further research on vertical PLMs but also expand the range of applications for PLMs.

Though many deep learning-based models have made great progress in vulnerability detection, we have no good understanding of these models, which limits the further advancement of model capability, understanding of the mechanism of model detection, and efficiency and safety of practical application of models. In this paper, we extensively and comprehensively investigate two types of state-of-the-art learning-based approaches (sequence-based and graph-based) by conducting experiments on a recently built large-scale dataset. We investigate seven research questions from five dimensions, namely model capabilities, model interpretation, model stability, ease of use of model, and model economy. We experimentally demonstrate the priority of sequence-based models and the limited abilities of both LLM (ChatGPT) and graph-based models. We explore the types of vulnerability that learning-based models skilled in and reveal the instability of the models though the input is subtlely semantical-equivalently changed. We empirically explain what the models have learned. We summarize the pre-processing as well as requirements for easily using the models. Finally, we initially induce the vital information for economically and safely practical usage of these models.

The use of Large Language Models (LLMs) has become ubiquitous, with abundant applications in computational creativity. One such application is fictional story generation. Fiction is a narrative that occurs in a story world that is slightly different than ours. With LLMs becoming writing partners, we question how suitable they are to generate fiction. This study investigates the ability of LLMs to maintain a state of world essential to generate fiction. Through a series of questions to nine LLMs, we find that only two models exhibit consistent worldview, while the rest are self-conflicting. Subsequent analysis of stories generated by four models revealed a strikingly uniform narrative pattern. This uniformity across models further suggests a lack of `state' necessary for fiction. We highlight the limitations of current LLMs in fiction writing and advocate for future research to test and create story worlds for LLMs to reside in. All code, dataset, and the generated responses can be found in https://github.com/tanny411/llm-reliability-and-consistency-evaluation.

Large Language Models (LLMs) have emerged as powerful conversational interfaces, and their application in process mining (PM) tasks has shown promising results. However, state-of-the-art LLMs struggle with complex scenarios that demand advanced reasoning capabilities. In the literature, two primary approaches have been proposed for implementing PM using LLMs: providing textual insights based on a textual abstraction of the process mining artifact, and generating code executable on the original artifact. This paper proposes utilizing the AI-Based Agents Workflow (AgWf) paradigm to enhance the effectiveness of PM on LLMs. This approach allows for: i) the decomposition of complex tasks into simpler workflows, and ii) the integration of deterministic tools with the domain knowledge of LLMs. We examine various implementations of AgWf and the types of AI-based tasks involved. Additionally, we discuss the CrewAI implementation framework and present examples related to process mining.

With significant advancements in Transformers LLMs, NLP has extended its reach into many research fields due to its enhanced capabilities in text generation and user interaction. One field benefiting greatly from these advancements is cybersecurity. In cybersecurity, many parameters that need to be protected and exchanged between senders and receivers are in the form of text and tabular data, making NLP a valuable tool in enhancing the security measures of communication protocols. This survey paper provides a comprehensive analysis of the utilization of Transformers and LLMs in cyber-threat detection systems. The methodology of paper selection and bibliometric analysis is outlined to establish a rigorous framework for evaluating existing research. The fundamentals of Transformers are discussed, including background information on various cyber-attacks and datasets commonly used in this field. The survey explores the application of Transformers in IDSs, focusing on different architectures such as Attention-based models, LLMs like BERT and GPT, CNN/LSTM-Transformer hybrids, emerging approaches like ViTs, among others. Furthermore, it explores the diverse environments and applications where Transformers and LLMs-based IDS have been implemented, including computer networks, IoT devices, critical infrastructure protection, cloud computing, SDN, as well as in autonomous vehicles. The paper also addresses research challenges and future directions in this area, identifying key issues such as interpretability, scalability, and adaptability to evolving threats, and more. Finally, the conclusion summarizes the findings and highlights the significance of Transformers and LLMs in enhancing cyber-threat detection capabilities, while also outlining potential avenues for further research and development.

Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated directly into the prompt. Despite the growing interest in optimizing prompts with few-shot examples, existing methods for prompt optimization are often resource-intensive or perform inadequately. In this work, we propose PrOmpting with Episodic Memory (POEM), a novel prompt optimization technique that is simple, efficient, and demonstrates strong generalization capabilities. We approach prompt optimization as a Reinforcement Learning (RL) challenge, using episodic memory to archive combinations of input data, permutations of few-shot examples, and the rewards observed during training. In the testing phase, we optimize the sequence of examples for each test query by selecting the sequence that yields the highest total rewards from the top-k most similar training examples in the episodic memory. Our results show that POEM outperforms recent techniques like TEMPERA and RLPrompt by over 5.3% in various text classification tasks. Furthermore, our approach adapts well to broader language understanding tasks, consistently outperforming conventional heuristic methods for ordering examples.