In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language Models (LLMs), existing works are highly dependent on large-scale labeled support sets, not always feasible in practical scenarios. To refine this approach, we focus primarily on an innovative selective annotation mechanism, which precedes the standard demonstration retrieval. We introduce the Language Model-based Determinant Point Process (LM-DPP) that simultaneously considers the uncertainty and diversity of unlabeled instances for optimal selection. Consequently, this yields a subset for annotation that strikes a trade-off between the two factors. We apply LM-DPP to various language models, including GPT-J, LlaMA, and GPT-3. Experimental results on 9 NLU and 2 Generation datasets demonstrate that LM-DPP can effectively select canonical examples. Further analysis reveals that LLMs benefit most significantly from subsets that are both low uncertainty and high diversity.

We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation models built upon Gemma2. These models provide robust, state-of-the-art predictions of safety risks across key harm types (sexually explicit, dangerous content, harassment, hate speech) in both user input and LLM-generated output. By evaluating on both public and internal benchmarks, we demonstrate superior performance compared to existing models, such as Llama Guard (+10.8\% AU-PRC on public benchmarks) and WildCard (+4.3\%). Additionally, we present a novel LLM-based data curation pipeline, adaptable to a variety of safety-related tasks and beyond. We have shown strong generalization performance for model trained mainly on synthetic data. By releasing ShieldGemma, we provide a valuable resource to the research community, advancing LLM safety and enabling the creation of more effective content moderation solutions for developers.

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.

The aspect-based sentiment analysis (ABSA) is a standard NLP task with numerous approaches and benchmarks, where large language models (LLM) represent the current state-of-the-art. We focus on ABSA subtasks based on Twitter/X data in underrepresented languages. On such narrow tasks, small tuned language models can often outperform universal large ones, providing available and cheap solutions. We fine-tune several LLMs (BERT, BERTweet, Llama2, Llama3, Mistral) for classification of sentiment towards Russia and Ukraine in the context of the ongoing military conflict. The training/testing dataset was obtained from the academic API from Twitter/X during 2023, narrowed to the languages of the V4 countries (Czech Republic, Slovakia, Poland, Hungary). Then we measure their performance under a variety of settings including translations, sentiment targets, in-context learning and more, using GPT4 as a reference model. We document several interesting phenomena demonstrating, among others, that some models are much better fine-tunable on multilingual Twitter tasks than others, and that they can reach the SOTA level with a very small training set. Finally we identify combinations of settings providing the best results.

Knob tuning plays a crucial role in optimizing databases by adjusting knobs to enhance database performance. However, traditional tuning methods often follow a Try-Collect-Adjust approach, proving inefficient and database-specific. Moreover, these methods are often opaque, making it challenging for DBAs to grasp the underlying decision-making process. The emergence of large language models (LLMs) like GPT-4 and Claude-3 has excelled in complex natural language tasks, yet their potential in database knob tuning remains largely unexplored. This study harnesses LLMs as experienced DBAs for knob-tuning tasks with carefully designed prompts. We identify three key subtasks in the tuning system: knob pruning, model initialization, and knob recommendation, proposing LLM-driven solutions to replace conventional methods for each subtask. We conduct extensive experiments to compare LLM-driven approaches against traditional methods across the subtasks to evaluate LLMs' efficacy in the knob tuning domain. Furthermore, we explore the adaptability of LLM-based solutions in diverse evaluation settings, encompassing new benchmarks, database engines, and hardware environments. Our findings reveal that LLMs not only match or surpass traditional methods but also exhibit notable interpretability by generating responses in a coherent ``chain-of-thought'' manner. We further observe that LLMs exhibit remarkable generalizability through simple adjustments in prompts, eliminating the necessity for additional training or extensive code modifications. Drawing insights from our experimental findings, we identify several opportunities for future research aimed at advancing the utilization of LLMs in the realm of database management.

This paper provides a thorough examination of recent developments in the field of multi-choice Machine Reading Comprehension (MRC). Focused on benchmark datasets, methodologies, challenges, and future trajectories, our goal is to offer researchers a comprehensive overview of the current landscape in multi-choice MRC. The analysis delves into 30 existing cloze-style and multiple-choice MRC benchmark datasets, employing a refined classification method based on attributes such as corpus style, domain, complexity, context style, question style, and answer style. This classification system enhances our understanding of each dataset's diverse attributes and categorizes them based on their complexity. Furthermore, the paper categorizes recent methodologies into Fine-tuned and Prompt-tuned methods. Fine-tuned methods involve adapting pre-trained language models (PLMs) to a specific task through retraining on domain-specific datasets, while prompt-tuned methods use prompts to guide PLM response generation, presenting potential applications in zero-shot or few-shot learning scenarios. By contributing to ongoing discussions, inspiring future research directions, and fostering innovations, this paper aims to propel multi-choice MRC towards new frontiers of achievement.

Endpoint Detection and Remediation (EDR) platforms are essential for identifying and responding to cyber threats. This study presents a novel approach using Large Language Models (LLMs) to detect Hands-on-Keyboard (HOK) cyberattacks. Our method involves converting endpoint activity data into narrative forms that LLMs can analyze to distinguish between normal operations and potential HOK attacks. We address the challenges of interpreting endpoint data by segmenting narratives into windows and employing a dual training strategy. The results demonstrate that LLM-based models have the potential to outperform traditional machine learning methods, offering a promising direction for enhancing EDR capabilities and apply LLMs in cybersecurity.

The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they need. However, most previous shopping assistants face two main problems: (1) task-specificity, which necessitates the development of different models for various tasks, thereby increasing development costs and limiting effectiveness; and (2) poor generalization, where the trained model performs inadequately on up-to-date products. To resolve these issues, we employ Large Language Models (LLMs) to construct an omnipotent assistant, leveraging their adeptness at handling multiple tasks and their superior generalization capability. Nonetheless, LLMs lack inherent knowledge of e-commerce concepts. To address this, we create an instruction dataset comprising 65,000 samples and diverse tasks, termed as EshopInstruct. Through instruction tuning on our dataset, the assistant, named LLaSA, demonstrates the potential to function as an omnipotent assistant. Additionally, we propose various inference optimization strategies to enhance performance with limited inference resources. In the Amazon KDD Cup 2024 Challenge, our proposed method, LLaSA, achieved an overall ranking of 3rd place on ShopBench, including 57 tasks and approximately 20,000 questions, and we secured top-5 rankings in each track, especially in track4, where we achieved the best performance result among all student teams. Our extensive practices fully demonstrate that LLMs possess the great potential to be competent e-commerce shopping assistants.

High-quality datasets of real-world vulnerabilities are enormously valuable for downstream research in software security, but existing datasets are typically small, require extensive manual effort to update, and are missing crucial features that such research needs. In this paper, we introduce ARVO: an Atlas of Reproducible Vulnerabilities in Open-source software. By sourcing vulnerabilities from C/C++ projects that Google's OSS-Fuzz discovered and implementing a reliable re-compilation system, we successfully reproduce more than 5,000 memory vulnerabilities across over 250 projects, each with a triggering input, the canonical developer-written patch for fixing the vulnerability, and the ability to automatically rebuild the project from source and run it at its vulnerable and patched revisions. Moreover, our dataset can be automatically updated as OSS-Fuzz finds new vulnerabilities, allowing it to grow over time. We provide a thorough characterization of the ARVO dataset, show that it can locate fixes more accurately than Google's own OSV reproduction effort, and demonstrate its value for future research through two case studies: firstly evaluating real-world LLM-based vulnerability repair, and secondly identifying over 300 falsely patched (still-active) zero-day vulnerabilities from projects improperly labeled by OSS-Fuzz.

Despite their impressive performance, large language models (LLMs) such as ChatGPT are known to pose important risks. One such set of risks arises from misplaced confidence, whether over-confidence or under-confidence, that the models have in their inference. While the former is well studied, the latter is not, leading to an asymmetry in understanding the comprehensive risk of the model based on misplaced confidence. In this paper, we address this asymmetry by defining two types of risk (decision and composite risk), and proposing an experimental framework consisting of a two-level inference architecture and appropriate metrics for measuring such risks in both discriminative and generative LLMs. The first level relies on a decision rule that determines whether the underlying language model should abstain from inference. The second level (which applies if the model does not abstain) is the model's inference. Detailed experiments on four natural language commonsense reasoning datasets using both an open-source ensemble-based RoBERTa model and ChatGPT, demonstrate the practical utility of the evaluation framework. For example, our results show that our framework can get an LLM to confidently respond to an extra 20.1% of low-risk inference tasks that other methods might misclassify as high-risk, and skip 19.8% of high-risk tasks, which would have been answered incorrectly.