Quantifying the uncertainty of predictions made by large language models (LLMs) in binary text classification tasks remains a challenge. Calibration, in the context of LLMs, refers to the alignment between the model's predicted probabilities and the actual correctness of its predictions. A well-calibrated model should produce probabilities that accurately reflect the likelihood of its predictions being correct. We propose a novel approach that utilizes the inductive Venn--Abers predictor (IVAP) to calibrate the probabilities associated with the output tokens corresponding to the binary labels. Our experiments on the BoolQ dataset using the Llama 2 model demonstrate that IVAP consistently outperforms the commonly used temperature scaling method for various label token choices, achieving well-calibrated probabilities while maintaining high predictive quality. Our findings contribute to the understanding of calibration techniques for LLMs and provide a practical solution for obtaining reliable uncertainty estimates in binary question answering tasks, enhancing the interpretability and trustworthiness of LLM predictions.

Artificial Intelligence (AI) is increasingly employed to enhance assistive technologies, yet it can fail in various ways. We conducted a systematic literature review of research into AI-based assistive technology for persons with visual impairments. Our study shows that most proposed technologies with a testable prototype have not been evaluated in a human study with members of the sight-loss community. Furthermore, many studies did not consider or report failure cases or possible risks. These findings highlight the importance of inclusive system evaluations and the necessity of standardizing methods for presenting and analyzing failure cases and threats when developing AI-based assistive technologies.

This tutorial explores the advancements and challenges in the development of Large Language Models (LLMs) such as ChatGPT and Gemini. It addresses inherent limitations like temporal knowledge cutoffs, mathematical inaccuracies, and the generation of incorrect information, proposing solutions like Retrieval Augmented Generation (RAG), Program-Aided Language Models (PAL), and frameworks such as ReAct and LangChain. The integration of these techniques enhances LLM performance and reliability, especially in multi-step reasoning and complex task execution. The paper also covers fine-tuning strategies, including instruction fine-tuning, parameter-efficient methods like LoRA, and Reinforcement Learning from Human Feedback (RLHF) as well as Reinforced Self-Training (ReST). Additionally, it provides a comprehensive survey of transformer architectures and training techniques for LLMs. The toolbox for implementing these techniques is publicly available at https://github.com/giorgioroffo/large_language_models_open_suite

This paper investigates how to efficiently deploy transformer-based neural networks on edge devices. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation. However, these methods are not designed with edge device deployment in mind, and do not leverage information about the hardware characteristics to improve efficiency. First, we show that the relationship between latency and workload size is governed by the GPU tail-effect. This relationship is used to create a token pruning schedule tailored for a pre-trained model and device pair. Second, we demonstrate a training-free token pruning method utilizing this relationship. This method achieves accuracy-latency trade-offs in a hardware aware manner. We show that for single batch inference, other methods may actually increase latency by 18.6-30.3% with respect to baseline, while we can reduce it by 9%. For similar latency (within 5.2%) across devices we achieve 78.6%-84.5% ImageNet1K accuracy, while the state-of-the-art, Token Merging, achieves 45.8%-85.4%.

Large Language Models (LLMs) have showcased exceptional capabilities in various domains, attracting significant interest from both academia and industry. Despite their impressive performance, the substantial size and computational demands of LLMs pose considerable challenges for practical deployment, particularly in environments with limited resources. The endeavor to compress language models while maintaining their accuracy has become a focal point of research. Among the various methods, knowledge distillation has emerged as an effective technique to enhance inference speed without greatly compromising performance. This paper presents a thorough survey from three aspects: method, evaluation, and application, exploring knowledge distillation techniques tailored specifically for LLMs. Specifically, we divide the methods into white-box KD and black-box KD to better illustrate their differences. Furthermore, we also explored the evaluation tasks and distillation effects between different distillation methods, and proposed directions for future research. Through in-depth understanding of the latest advancements and practical applications, this survey provides valuable resources for researchers, paving the way for sustained progress in this field.

Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. The benchmark is designed to systematically assess current model capabilities in discovery tasks and provide a useful resource for improving them. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering, by manually deriving discovery workflows from published papers to approximate the real-world challenges faced by researchers, where each task is defined by a dataset, its metadata, and a discovery goal in natural language. We additionally provide 903 synthetic tasks to conduct controlled evaluations across task complexity. Furthermore, our structured formalism of data-driven discovery enables a facet-based evaluation that provides useful insights into different failure modes. We evaluate several popular LLM-based reasoning frameworks using both open and closed LLMs as baselines on DiscoveryBench and find that even the best system scores only 25%. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.

Graph classification is a pivotal challenge in machine learning, especially within the realm of graph-based data, given its importance in numerous real-world applications such as social network analysis, recommendation systems, and bioinformatics. Despite its significance, graph classification faces several hurdles, including adapting to diverse prediction tasks, training across multiple target domains, and handling small-sample prediction scenarios. Current methods often tackle these challenges individually, leading to fragmented solutions that lack a holistic approach to the overarching problem. In this paper, we propose an algorithm aimed at addressing the aforementioned challenges. By incorporating insights from various types of tasks, our method aims to enhance adaptability, scalability, and generalizability in graph classification. Motivated by the recognition that the underlying subgraph plays a crucial role in GNN prediction, while the remainder is task-irrelevant, we introduce the Core Knowledge Learning (\method{}) framework for graph adaptation and scalability learning. \method{} comprises several key modules, including the core subgraph knowledge submodule, graph domain adaptation module, and few-shot learning module for downstream tasks. Each module is tailored to tackle specific challenges in graph classification, such as domain shift, label inconsistencies, and data scarcity. By learning the core subgraph of the entire graph, we focus on the most pertinent features for task relevance. Consequently, our method offers benefits such as improved model performance, increased domain adaptability, and enhanced robustness to domain variations. Experimental results demonstrate significant performance enhancements achieved by our method compared to state-of-the-art approaches.

AI regulations are expected to prohibit machine learning models from using sensitive attributes during training. However, the latest Natural Language Processing (NLP) classifiers, which rely on deep learning, operate as black-box systems, complicating the detection and remediation of such misuse. Traditional bias mitigation methods in NLP aim for comparable performance across different groups based on attributes like gender or race but fail to address the underlying issue of reliance on protected attributes. To partly fix that, we introduce NLPGuard, a framework for mitigating the reliance on protected attributes in NLP classifiers. NLPGuard takes an unlabeled dataset, an existing NLP classifier, and its training data as input, producing a modified training dataset that significantly reduces dependence on protected attributes without compromising accuracy. NLPGuard is applied to three classification tasks: identifying toxic language, sentiment analysis, and occupation classification. Our evaluation shows that current NLP classifiers heavily depend on protected attributes, with up to $23\%$ of the most predictive words associated with these attributes. However, NLPGuard effectively reduces this reliance by up to $79\%$, while slightly improving accuracy.

This paper presents the POLygraph dataset, a unique resource for fake news detection in Polish. The dataset, created by an interdisciplinary team, is composed of two parts: the "fake-or-not" dataset with 11,360 pairs of news articles (identified by their URLs) and corresponding labels, and the "fake-they-say" dataset with 5,082 news articles (identified by their URLs) and tweets commenting on them. Unlike existing datasets, POLygraph encompasses a variety of approaches from source literature, providing a comprehensive resource for fake news detection. The data was collected through manual annotation by expert and non-expert annotators. The project also developed a software tool that uses advanced machine learning techniques to analyze the data and determine content authenticity. The tool and dataset are expected to benefit various entities, from public sector institutions to publishers and fact-checking organizations. Further dataset exploration will foster fake news detection and potentially stimulate the implementation of similar models in other languages. The paper focuses on the creation and composition of the dataset, so it does not include a detailed evaluation of the software tool for content authenticity analysis, which is planned at a later stage of the project.

A polyglot is a file that is valid in two or more formats. Polyglot files pose a problem for malware detection systems that route files to format-specific detectors/signatures, as well as file upload and sanitization tools. In this work we found that existing file-format and embedded-file detection tools, even those developed specifically for polyglot files, fail to reliably detect polyglot files used in the wild, leaving organizations vulnerable to attack. To address this issue, we studied the use of polyglot files by malicious actors in the wild, finding $30$ polyglot samples and $15$ attack chains that leveraged polyglot files. In this report, we highlight two well-known APTs whose cyber attack chains relied on polyglot files to bypass detection mechanisms. Using knowledge from our survey of polyglot usage in the wild -- the first of its kind -- we created a novel data set based on adversary techniques. We then trained a machine learning detection solution, PolyConv, using this data set. PolyConv achieves a precision-recall area-under-curve score of $0.999$ with an F1 score of $99.20$% for polyglot detection and $99.47$% for file-format identification, significantly outperforming all other tools tested. We developed a content disarmament and reconstruction tool, ImSan, that successfully sanitized $100$% of the tested image-based polyglots, which were the most common type found via the survey. Our work provides concrete tools and suggestions to enable defenders to better defend themselves against polyglot files, as well as directions for future work to create more robust file specifications and methods of disarmament.