Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this article, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional deep learning models.

Artificial Intelligence (AI) is making a profound impact in almost every domain. A vital enabler of its great success is the availability of abundant and high-quality data for building machine learning models. Recently, the role of data in AI has been significantly magnified, giving rise to the emerging concept of data-centric AI . The attention of researchers and practitioners has gradually shifted from advancing model design to enhancing the quality and quantity of the data. In this survey, we discuss the necessity of data-centric AI, followed by a holistic view of three general data-centric goals (training data development, inference data development, and data maintenance) and the representative methods. We also organize the existing literature from automation and collaboration perspectives, discuss the challenges, and tabulate the benchmarks for various tasks. We believe this is the first comprehensive survey that provides a global view of a spectrum of tasks across various stages of the data lifecycle. We hope it can help the readers efficiently grasp a broad picture of this field, and equip them with the techniques and further research ideas to systematically engineer data for building AI systems. A companion list of data-centric AI resources will be regularly updated on https://github.com/daochenzha/data-centric-AI .

The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations. By comparing the LLM's internal representation of various languages against a baseline derived from English, we can assess the model's multilingual capabilities in a robust and language-agnostic manner. Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores, underscoring the effectiveness of our metric in assessing language-specific capabilities. Besides, the experiments show that there is a strong correlation between the LLM’s performance in different languages and the proportion of those languages in its pre-training corpus. These insights underscore the efficacy of the Language Ranker as a tool for evaluating LLM performance across different languages, particularly those with limited resources.

Explainable artificial intelligence (XAI) systems aim to provide users with information to help them better understand computational models and reason about why outputs were generated. However, there are many different ways an XAI interface might present explanations, which makes designing an appropriate and effective interface an important and challenging task. Our work investigates how different types and amounts of explanatory information affect user ability to utilize explanations to understand system behavior and improve task performance. The presented research employs a system for detecting the truthfulness of news statements. In a controlled experiment, participants were tasked with using the system to assess news statements as well as to learn to predict the output of the AI. Our experiment compares various levels of explanatory information to contribute empirical data about how explanation detail can influence utility. The results show that more explanation information improves participant understanding of AI models, but the benefits come at the cost of time and attention needed to make sense of the explanation.

Understanding the spatial distribution of palms in tropical forests is essential for ecological monitoring, conservation strategies, and the sustainable integration of natural forest products into local and global supply chains. However, the analysis of remotely sensed data are challenged by overlapping palm and tree crowns, uneven shading across the canopy surface, and the heterogeneous nature of the forest landscapes, which often affect the performance of palm detection and segmentation algorithms. To overcome these issues, we introduce PalmDSNet, a deep learning framework for efficient detection, segmentation, and counting of canopy palms. To model spatial patterns, we introduce a bimodal reproduction algorithm that simulates palm propagation based on PalmDSNet outputs. We used UAV-captured imagery to create orthomosaics from 21 sites across western Ecuadorian tropical forests, covering a gradient from the everwet Chocó forests near Colombia to the drier forests of southwestern Ecuador. Expert annotations were used to create a comprehensive dataset, including 7,356 bounding boxes on image patches and 7,603 palm centers across five orthomosaics, encompassing a total area of 449 hectares. By integrating detection and spatial modeling, we effectively simulate the spatial distribution of palms in diverse and dense tropical environments, validating its utility for advanced applications in tropical forest monitoring and remote sensing analysis. The dataset can be accessed at 10.5281/zenodo.13822508, and the code to replicate the study is available at github.com/ckn3/palm-ds-sp.

Immunotherapy has become a cornerstone in the treatment of advanced gastric cancer (GC). However, identifying reliable predictive biomarkers remains a considerable challenge. This study demonstrates the potential of integrating multimodal baseline data, including computed tomography scan images and digital H&E-stained pathology images, with biological interpretation to predict the response to immunotherapy-based combination therapy using a multicenter cohort of 298 GC patients. By employing seven machine learning approaches, we developed a radiopathomics signature (RPS) to predict treatment response and stratify prognostic risk in GC. The RPS demonstrated area under the receiver-operating-characteristic curves (AUCs) of 0.978 (95 % CI, 0.950-1.000), 0.863 (95 % CI, 0.744-0.982), and 0.822 (95 % CI, 0.668-0.975) in the training, internal validation, and external validation cohorts, respectively, outperforming conventional biomarkers such as CPS, MSI-H, EBV, and HER-2. Kaplan-Meier analysis revealed significant differences of survival between high- and low-risk groups, especially in advanced-stage and non-surgical patients. Additionally, genetic analyses revealed that the RPS correlates with enhanced immune regulation pathways and increased infiltration of memory B cells. The interpretable RPS provides accurate predictions for treatment response and prognosis in GC and holds potential for guiding more precise, patient-specific treatment strategies while offering insights into immune-related mechanisms.