Specifying legal requirements for software systems to ensure their compliance with the applicable regulations is a major concern to requirements engineering (RE). Personal data which is collected by an organization is often shared with other organizations to perform certain processing activities. In such cases, the General Data Protection Regulation (GDPR) requires issuing a data processing agreement (DPA) which regulates the processing and further ensures that personal data remains protected. Violating GDPR can lead to huge fines reaching to billions of Euros. Software systems involving personal data processing must adhere to the legal obligations stipulated in GDPR and outlined in DPAs. Requirements engineers can elicit from DPAs legal requirements for regulating the data processing activities in software systems. Checking the completeness of a DPA according to the GDPR provisions is therefore an essential prerequisite to ensure that the elicited requirements are complete. Analyzing DPAs entirely manually is time consuming and requires adequate legal expertise. In this paper, we propose an automation strategy to address the completeness checking of DPAs against GDPR. Specifically, we pursue ten alternative solutions which are enabled by different technologies, namely traditional machine learning, deep learning, language modeling, and few-shot learning. The goal of our work is to empirically examine how these different technologies fare in the legal domain. We computed F2 score on a set of 30 real DPAs. Our evaluation shows that best-performing solutions yield F2 score of 86.7% and 89.7% are based on pre-trained BERT and RoBERTa language models. Our analysis further shows that other alternative solutions based on deep learning (e.g., BiLSTM) and few-shot learning (e.g., SetFit) can achieve comparable accuracy, yet are more efficient to develop.
Scoring student-drawn models is time-consuming. Recently released GPT-4V provides a unique opportunity to advance scientific modeling practices by leveraging the powerful image processing capability. To test this ability specifically for automatic scoring, we developed a method NERIF (Notation-Enhanced Rubric Instruction for Few-shot Learning) employing instructional note and rubrics to prompt GPT-4V to score students' drawn models for science phenomena. We randomly selected a set of balanced data (N = 900) that includes student-drawn models for six modeling assessment tasks. Each model received a score from GPT-4V ranging at three levels: 'Beginning,' 'Developing,' or 'Proficient' according to scoring rubrics. GPT-4V scores were compared with human experts' scores to calculate scoring accuracy. Results show that GPT-4V's average scoring accuracy was mean =.51, SD = .037. Specifically, average scoring accuracy was .64 for the 'Beginning' class, .62 for the 'Developing' class, and .26 for the 'Proficient' class, indicating that more proficient models are more challenging to score. Further qualitative study reveals how GPT-4V retrieves information from image input, including problem context, example evaluations provided by human coders, and students' drawing models. We also uncovered how GPT-4V catches the characteristics of student-drawn models and narrates them in natural language. At last, we demonstrated how GPT-4V assigns scores to student-drawn models according to the given scoring rubric and instructional notes. Our findings suggest that the NERIF is an effective approach for employing GPT-4V to score drawn models. Even though there is space for GPT-4V to improve scoring accuracy, some mis-assigned scores seemed interpretable to experts. The results of this study show that utilizing GPT-4V for automatic scoring of student-drawn models is promising.
Traditional methods like Graph Convolutional Networks (GCNs) face challenges with limited data and class imbalance, leading to suboptimal performance in graph classification tasks during toxicity prediction of molecules as a whole. To address these issues, we harness the power of Graph Isomorphic Networks, Multi Headed Attention and Free Large-scale Adversarial Augmentation separately on Graphs for precisely capturing the structural data of molecules and their toxicological properties. Additionally, we incorporate Few-Shot Learning to improve the model's generalization with limited annotated samples. Extensive experiments on a diverse toxicology dataset demonstrate that our method achieves an impressive state-of-art AUC-ROC value of 0.816, surpassing the baseline GCN model by 11.4%. This highlights the significance of our proposed methodology and Few Shot Learning in advancing Toxic Molecular Classification, with the potential to enhance drug discovery and environmental risk assessment processes.
Given the increasing availability of RNA-seq data and its complex and heterogeneous nature, there has been growing interest in applying AI/machine learning methodologies to work with such data modalities. However, because omics data is characterized by high dimensionality and low sample size (HDLSS), current attempts at integrating AI in this domain require significant human guidance and expertise to mitigate overfitting. In this work we look at how transfer learning can be improved to learn from small RNA-seq sample sizes without significant human interference. The strategy is to gain general prior knowledge about a particular domain of data (e.g. RNA-seq data) by pre-training on a general task with a large aggregate of data, then fine-tuning to various specific, downstream target tasks in the same domain. Because previous attempts have shown traditional transfer learning failing on HLDSS, we propose to improve performance by using Guided Transfer Learning (GTL). Collaborating with Robots Go Mental, the AI we deploy here not only learns good initial parameters during pre-training, but also learns inductive biases that affect how the AI learns downstream tasks. In this approach, we first pre-trained on recount3 data, a collection of over 400,000 mouse RNA-seq samples sourced from thousands of individual studies. With such a large collection, patterns of expression between the ~30,000 genes in mammalian systems were pre-determined. Such patterns were sufficient for the pre-trained AI agent to efficiently learn new downstream tasks involving RNA-seq datasets with very low sample sizes and performed notably better on few-shot learning tasks compared to the same model without pre-training.
This survey paper presents a brief overview of recent research on graph data augmentation and few-shot learning. It covers various techniques for graph data augmentation, including node and edge perturbation, graph coarsening, and graph generation, as well as the latest developments in few-shot learning, such as meta-learning and model-agnostic meta-learning. The paper explores these areas in depth and delves into further sub classifications. Rule based approaches and learning based approaches are surveyed under graph augmentation techniques. Few-Shot Learning on graphs is also studied in terms of metric learning techniques and optimization-based techniques. In all, this paper provides an extensive array of techniques that can be employed in solving graph processing problems faced in low-data scenarios.
Developing machine learning models to characterize political polarization on online social media presents significant challenges. These challenges mainly stem from various factors such as the lack of annotated data, presence of noise in social media datasets, and the sheer volume of data. The common research practice typically examines the biased structure of online user communities for a given topic or qualitatively measuring the impacts of polarized topics on social media. However, there is limited work focusing on analyzing polarization at the ground-level, specifically in the social media posts themselves. Such existing analysis heavily relies on annotated data, which often requires laborious human labeling, offers labels only to specific problems, and lacks the ability to determine the near-future bias state of a social media conversations. Understanding the degree of political orientation conveyed in social media posts is crucial for quantifying the bias of online user communities and investigating the spread of polarized content. In this work, we first introduce two heuristic methods that leverage on news media bias and post content to label social media posts. Next, we compare the efficacy and quality of heuristically labeled dataset with a randomly sampled human-annotated dataset. Additionally, we demonstrate that current machine learning models can exhibit improved performance in predicting political orientation of social media posts, employing both traditional supervised learning and few-shot learning setups. We conduct experiments using the proposed heuristic methods and machine learning approaches to predict the political orientation of posts collected from two social media forums with diverse political ideologies: Gab and Twitter.
Recent advances in large language models (LLMs) have opened new possibilities for artificial intelligence applications in finance. In this paper, we provide a practical survey focused on two key aspects of utilizing LLMs for financial tasks: existing solutions and guidance for adoption. First, we review current approaches employing LLMs in finance, including leveraging pretrained models via zero-shot or few-shot learning, fine-tuning on domain-specific data, and training custom LLMs from scratch. We summarize key models and evaluate their performance improvements on financial natural language processing tasks. Second, we propose a decision framework to guide financial professionals in selecting the appropriate LLM solution based on their use case constraints around data, compute, and performance needs. The framework provides a pathway from lightweight experimentation to heavy investment in customized LLMs. Lastly, we discuss limitations and challenges around leveraging LLMs in financial applications. Overall, this survey aims to synthesize the state-of-the-art and provide a roadmap for responsibly applying LLMs to advance financial AI.
In recent years, the field of 3D self-supervised learning has witnessed significant progress, resulting in the emergence of Multi-Modality Masked AutoEncoders (MAE) methods that leverage both 2D images and 3D point clouds for pre-training. However, a notable limitation of these approaches is that they do not fully utilize the multi-view attributes inherent in 3D point clouds, which is crucial for a deeper understanding of 3D structures. Building upon this insight, we introduce a novel approach employing a 3D to multi-view masked autoencoder to fully harness the multi-modal attributes of 3D point clouds. To be specific, our method uses the encoded tokens from 3D masked point clouds to generate original point clouds and multi-view depth images across various poses. This approach not only enriches the model's comprehension of geometric structures but also leverages the inherent multi-modal properties of point clouds. Our experiments illustrate the effectiveness of the proposed method for different tasks and under different settings. Remarkably, our method outperforms state-of-the-art counterparts by a large margin in a variety of downstream tasks, including 3D object classification, few-shot learning, part segmentation, and 3D object detection. Code will be available at: https://github.com/Zhimin-C/Multiview-MAE
Human-level driving is an ultimate goal of autonomous driving. Conventional approaches formulate autonomous driving as a perception-prediction-planning framework, yet their systems do not capitalize on the inherent reasoning ability and experiential knowledge of humans. In this paper, we propose a fundamental paradigm shift from current pipelines, exploiting Large Language Models (LLMs) as a cognitive agent to integrate human-like intelligence into autonomous driving systems. Our approach, termed Agent-Driver, transforms the traditional autonomous driving pipeline by introducing a versatile tool library accessible via function calls, a cognitive memory of common sense and experiential knowledge for decision-making, and a reasoning engine capable of chain-of-thought reasoning, task planning, motion planning, and self-reflection. Powered by LLMs, our Agent-Driver is endowed with intuitive common sense and robust reasoning capabilities, thus enabling a more nuanced, human-like approach to autonomous driving. We evaluate our approach on the large-scale nuScenes benchmark, and extensive experiments substantiate that our Agent-Driver significantly outperforms the state-of-the-art driving methods by a large margin. Our approach also demonstrates superior interpretability and few-shot learning ability to these methods.
In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises. The working principle was based on the ultrasound Doppler sensing with the device built-in hardware. Applying such a lab-environment trained model on realistic application variations causes a significant drop in performance, and thus decimate its applicability. The reason of the reduced performance can be manifold. It could be induced by the user, environment, and device variations in realistic scenarios. Such scenarios are often more complex and diverse, which can be challenging to anticipate in the initial training data. To study and overcome this issue, this paper presents a database with controlled and uncontrolled subsets of fitness exercises. We propose two concepts to utilize small adaption data to successfully improve model generalization in an uncontrolled environment, increasing the recognition accuracy by two to six folds compared to the baseline for different users.
Despite the prevalence of tabular datasets, few-shot learning remains under-explored within this domain. Existing few-shot methods are not directly applicable to tabular datasets due to varying column relationships, meanings, and permutational invariance. To address these challenges, we propose FLAT-a novel approach to tabular few-shot learning, encompassing knowledge sharing between datasets with heterogeneous feature spaces. Utilizing an encoder inspired by Dataset2Vec, FLAT learns low-dimensional embeddings of datasets and their individual columns, which facilitate knowledge transfer and generalization to previously unseen datasets. A decoder network parametrizes the predictive target network, implemented as a Graph Attention Network, to accommodate the heterogeneous nature of tabular datasets. Experiments on a diverse collection of 118 UCI datasets demonstrate FLAT's successful generalization to new tabular datasets and a considerable improvement over the baselines.
We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessing the capabilities of these LLMs has become a challenging and critical issue due to potential data contamination, and it wastes dozens of time and effort for researchers and engineers to download and try those contaminated models. To save our precious time, we propose a novel and useful method, Clean-Eval, which mitigates the issue of data contamination and evaluates the LLMs in a cleaner manner. Clean-Eval employs an LLM to paraphrase and back-translate the contaminated data into a candidate set, generating expressions with the same meaning but in different surface forms. A semantic detector is then used to filter the generated low-quality samples to narrow down this candidate set. The best candidate is finally selected from this set based on the BLEURT score. According to human assessment, this best candidate is semantically similar to the original contamination data but expressed differently. All candidates can form a new benchmark to evaluate the model. Our experiments illustrate that Clean-Eval substantially restores the actual evaluation results on contaminated LLMs under both few-shot learning and fine-tuning scenarios.
Recently, work in NLP has shifted to few-shot (in-context) learning, with large language models (LLMs) performing well across a range of tasks. However, while fairness evaluations have become a standard for supervised methods, little is known about the fairness of LLMs as prediction systems. Further, common standard methods for fairness involve access to models weights or are applied during finetuning, which are not applicable in few-shot learning. Do LLMs exhibit prediction biases when used for standard NLP tasks? In this work, we explore the effect of shots, which directly affect the performance of models, on the fairness of LLMs as NLP classification systems. We consider how different shot selection strategies, both existing and new demographically sensitive methods, affect model fairness across three standard fairness datasets. We discuss how future work can include LLM fairness evaluations.
Detecting COVID-19 patients using Computed Tomography (CT) images of the lungs is an active area of research. Datasets of CT images from COVID-19 patients are becoming available. Deep learning (DL) solutions and in particular Convolutional Neural Networks (CNN) have achieved impressive results for the classification of COVID-19 CT images, but only when the training and testing take place within the same dataset. Work on the cross-dataset problem is still limited and the achieved results are low. Our work tackles the cross-dataset problem through a Domain Adaptation (DA) technique with deep learning. Our proposed solution, COVID19-DANet, is based on pre-trained CNN backbone for feature extraction. For this task, we select the pre-trained Efficientnet-B3 CNN because it has achieved impressive classification accuracy in previous work. The backbone CNN is followed by a prototypical layer which is a concept borrowed from prototypical networks in few-shot learning (FSL). It computes a cosine distance between given samples and the class prototypes and then converts them to class probabilities using the Softmax function. To train the COVID19-DANet model, we propose a combined loss function that is composed of the standard cross-entropy loss for class discrimination and another entropy loss computed over the unlabelled target set only. This so-called unlabelled target entropy loss is minimized and maximized in an alternative fashion, to reach the two objectives of class discrimination and domain invariance. COVID19-DANet is tested under four cross-dataset scenarios using the SARS-CoV-2-CT and COVID19-CT datasets and has achieved encouraging results compared to recent work in the literature.
In pathology, the rarity of certain diseases and the complexity in annotating pathological images significantly hinder the creation of extensive, high-quality datasets. This limitation impedes the progress of deep learning-assisted diagnostic systems in pathology. Consequently, it becomes imperative to devise a technology that can discern new disease categories from a minimal number of annotated examples. Such a technology would substantially advance deep learning models for rare diseases. Addressing this need, we introduce the Dual-channel Prototype Network (DCPN), rooted in the few-shot learning paradigm, to tackle the challenge of classifying pathological images with limited samples. DCPN augments the Pyramid Vision Transformer (PVT) framework for few-shot classification via self-supervised learning and integrates it with convolutional neural networks. This combination forms a dual-channel architecture that extracts multi-scale, highly precise pathological features. The approach enhances the versatility of prototype representations and elevates the efficacy of prototype networks in few-shot pathological image classification tasks. We evaluated DCPN using three publicly available pathological datasets, configuring small-sample classification tasks that mirror varying degrees of clinical scenario domain shifts. Our experimental findings robustly affirm DCPN's superiority in few-shot pathological image classification, particularly in tasks within the same domain, where it achieves the benchmarks of supervised learning.
In-context learning (ICL) has shown impressive results in few-shot learning tasks, yet its underlying mechanism is still not fully understood. A recent line of work suggests that ICL performs gradient descent (GD)-based optimization implicitly. While appealing, much of the research focuses on simplified settings, where the parameters of a shallow model are optimized. In this work, we revisit evidence for ICL-GD correspondence on realistic NLP tasks and models. We find gaps in evaluation, both in terms of problematic metrics and insufficient baselines. We show that surprisingly, even untrained models achieve comparable ICL-GD similarity scores despite not exhibiting ICL. Next, we explore a major discrepancy in the flow of information throughout the model between ICL and GD, which we term Layer Causality. We propose a simple GD-based optimization procedure that respects layer causality, and show it improves similarity scores significantly.
The sparsity of labelled data is an obstacle to the development of Relation Extraction models and the completion of databases in various biomedical areas. While being of high interest in drug-discovery, the natural-products literature, reporting the identification of potential bioactive compounds from organisms, is a concrete example of such an overlooked topic. To mark the start of this new task, we created the first curated evaluation dataset and extracted literature items from the LOTUS database to build training sets. To this end, we developed a new sampler inspired by diversity metrics in ecology, named Greedy Maximum Entropy sampler, or GME-sampler (https://github.com/idiap/gme-sampler). The strategic optimization of both balance and diversity of the selected items in the evaluation set is important given the resource-intensive nature of manual curation. After quantifying the noise in the training set, in the form of discrepancies between the input abstracts text and the expected output labels, we explored different strategies accordingly. Framing the task as an end-to-end Relation Extraction, we evaluated the performance of standard fine-tuning as a generative task and few-shot learning with open Large Language Models (LLaMA 7B-65B). In addition to their evaluation in few-shot settings, we explore the potential of open Large Language Models (Vicuna-13B) as synthetic data generator and propose a new workflow for this purpose. All evaluated models exhibited substantial improvements when fine-tuned on synthetic abstracts rather than the original noisy data. We provide our best performing (f1-score=59.0) BioGPT-Large model for end-to-end RE of natural-products relationships along with all the generated synthetic data and the evaluation dataset. See more details at https://github.com/idiap/abroad-re.
Knowledge-Enhanced Pre-trained Language Models (KEPLMs) improve the performance of various downstream NLP tasks by injecting knowledge facts from large-scale Knowledge Graphs (KGs). However, existing methods for pre-training KEPLMs with relational triples are difficult to be adapted to close domains due to the lack of sufficient domain graph semantics. In this paper, we propose a Knowledge-enhanced lANGuAge Representation learning framework for various clOsed dOmains (KANGAROO) via capturing the implicit graph structure among the entities. Specifically, since the entity coverage rates of closed-domain KGs can be relatively low and may exhibit the global sparsity phenomenon for knowledge injection, we consider not only the shallow relational representations of triples but also the hyperbolic embeddings of deep hierarchical entity-class structures for effective knowledge fusion.Moreover, as two closed-domain entities under the same entity-class often have locally dense neighbor subgraphs counted by max point biconnected component, we further propose a data augmentation strategy based on contrastive learning over subgraphs to construct hard negative samples of higher quality. It makes the underlying KELPMs better distinguish the semantics of these neighboring entities to further complement the global semantic sparsity. In the experiments, we evaluate KANGAROO over various knowledge-aware and general NLP tasks in both full and few-shot learning settings, outperforming various KEPLM training paradigms performance in closed-domains significantly.
The surgical removal of head and neck tumors requires safe margins, which are usually confirmed intraoperatively by means of frozen sections. This method is, in itself, an oversampling procedure, which has a relatively low sensitivity compared to the definitive tissue analysis on paraffin-embedded sections. Confocal laser endomicroscopy (CLE) is an in-vivo imaging technique that has shown its potential in the live optical biopsy of tissue. An automated analysis of this notoriously difficult to interpret modality would help surgeons. However, the images of CLE show a wide variability of patterns, caused both by individual factors but also, and most strongly, by the anatomical structures of the imaged tissue, making it a challenging pattern recognition task. In this work, we evaluate four popular few shot learning (FSL) methods towards their capability of generalizing to unseen anatomical domains in CLE images. We evaluate this on images of sinunasal tumors (SNT) from five patients and on images of the vocal folds (VF) from 11 patients using a cross-validation scheme. The best respective approach reached a median accuracy of 79.6% on the rather homogeneous VF dataset, but only of 61.6% for the highly diverse SNT dataset. Our results indicate that FSL on CLE images is viable, but strongly affected by the number of patients, as well as the diversity of anatomical patterns.
Recent research highlights the significant potential of ChatGPT for text annotation in social science research. However, ChatGPT is a closed-source product which has major drawbacks with regards to transparency, reproducibility, cost, and data protection. Recent advances in open-source (OS) large language models (LLMs) offer alternatives which remedy these challenges. This means that it is important to evaluate the performance of OS LLMs relative to ChatGPT and standard approaches to supervised machine learning classification. We conduct a systematic comparative evaluation of the performance of a range of OS LLM models alongside ChatGPT, using both zero- and few-shot learning as well as generic and custom prompts, with results compared to more traditional supervised classification models. Using a new dataset of Tweets from US news media, and focusing on simple binary text annotation tasks for standard social science concepts, we find significant variation in the performance of ChatGPT and OS models across the tasks, and that supervised classifiers consistently outperform both. Given the unreliable performance of ChatGPT and the significant challenges it poses to Open Science we advise against using ChatGPT for substantive text annotation tasks in social science research.