Large language model for post‐earthquake structural damage assessment of buildings

ZVQAF: Zero-shot visual question answering with feedback from large language models

Large Language Models (LLMs) have become a crucial tool in Visual Question Answering (VQA) for handling knowledge-intensive questions in few-shot or zero-shot scenarios. However, their reliance on massive training datasets often causes them to inherit language biases during the acquisition of knowledge. This limitation imposes two key constraints on existing methods: (1) LLM predictions become less reliable due to bias exploitation, and (2) despite strong knowledge reasoning capabilities, LLMs still struggle with out-of-distribution (OOD) generalization. To address these issues, we propose Object Attribute Description Promoter (OAD-Promoter), a novel approach for enhancing LLM-based VQA by mitigating language bias and improving domain-shift robustness. OAD-Promoter comprises three components: the Object-concentrated Example Generation (OEG) module, the Memory Knowledge Assistance (MKA) module, and the OAD Prompt. The OEG module generates global captions and object-concentrated samples, jointly enhancing visual information input to the LLM and mitigating bias through complementary global and regional visual cues. The MKA module assists the LLM in handling OOD samples by retrieving relevant knowledge from stored examples to support questions from unseen domains. Finally, the OAD Prompt integrates the outputs of the preceding modules to optimize LLM inference. Experiments demonstrate that OAD-Promoter significantly improves the performance of LLM-based VQA methods in few-shot or zero-shot settings, achieving new state-of-the-art results.

Abstract. Rapid and accurate assessment of the state of buildings in the aftermath of a disaster event is critical for an effective and timely response. For rapid damage assessment of buildings, the utility of remote sensing (RS) technology has been widely researched, with focus on a range of platforms and sensors. However, RS-based approaches still have limitations to assess structural integrity and the specific damage status of individual buildings. Structural integrity refers to the ability of a building to hold the entire structure. Consequently, ground-based assessment conducted by structural engineers and first responders is still required. This paper demonstrates the concept of mobile augmented reality (mAR) to improve performance of building damage and safety assessment in situ. Mobile AR provides a means to superimpose various types of reference or pre-disaster information (virtual data) on actual post-disaster building data (real buildings). To adopt mobile AR, this study defines a conceptual framework based on the level of complexity (LOC). The framework consists of four LOCs, and for each of these, the data types, required processing steps, AR implementation and use for damage assessment are described. Based on this conceptualization we demonstrate prototypes of mAR for both indoor and outdoor purposes. Finally, we conduct a user evaluation of the prototypes to validate the mAR approach for building damage and safety assessment.

Modular Arabic VQA System Using Pre-Trained Models

Multimodal Visual Question Answering (VQA) in science requires reasoning over domain-specific text and diagrams. While large language models (LLMs) excel at text reasoning, they often rely on image captions, losing spatial and relational details. The ScienceQA benchmark (21k questions with lectures and diagrams) highlights this gap. Chain-of-Thought (CoT) prompting improves reasoning but suffers from error propagation and long context dependencies. Atom-of-Thought (AoT) addresses these issues by decomposing problems into independent, self-contained "atoms" organized in a Directed Acyclic Graph (DAG), each conditioned only on the question and visual input. This modular, DAG-based structure minimizes dependencies, reduces error accumulation, and enables parallel reasoning. This thesis is the first to explore AoT in multimodal VQA. The contributions are: (1) adapting AoT for visual-text integration, (2) instruction-tuning LLaVA-7B with AoT rationales generated via GPT, and (3) evaluating accuracy and reasoning clarity on ScienceQA. Results show that in zero-shot evaluation, fine-tuned LLaVA-7B achieves 51.97% accuracy (vs. 51.50% base), while GPT-4o-mini with AoT reaches 83.09%, surpassing the GPT-3 CoT baseline of 75.17%.

Visual question answering (VQA) research has garnered increasing attention in recent years. It is considered a visual Turing test because it requires a computer to respond to textual questions based on an image. Expertise in computer vision, natural language processing, knowledge understanding, and reasoning is required to solve the problem of VQA. Most techniques employed for VQA consist of models that are developed to learn the combination of image and question features along with the expected answer. The techniques chosen for image and question feature extraction and combining the features change with each model. This method of teaching a model of the question–answer pattern is ineffective for queries that involve counting and reasoning. This approach also requires considerable resources and large datasets for the training. The general VQA datasets feature a restricted number of items as responses to counting questions ([Formula: see text]), and the distribution of the answers is not uniform. To investigate these issues in VQA, we created synthetic datasets that could be modified to adjust the number of objects in the image and the amount of occlusion. Specifically, a zero-shot learning VQA system was devised for counting-related questions that provide answers by analyzing the output of an object detector and the query keywords. Using synthetic datasets, our model generated 100% correct results. Testing on the benchmark datasets task directed image understanding challenge (TDIUC) and TallyQA-simple indicated that the proposed model matched the performance of the learning-based baseline models. This methodology can be used efficiently for counting VQA questions confined to certain domains when the number of items to be counted is significant.

Visual Question Answering (VQA) in remote sensing (RS) is pivotal for interpreting Earth observation data. However, existing RS VQA datasets are constrained by limitations in annotation richness, question diversity, and the assessment of specific reasoning capabilities. This paper introduces Remote Sensing Vision Language Model Question Answering (RSVLM-QA) dataset, a new large-scale, content-rich VQA dataset for the RS domain. RSVLM-QA is constructed by integrating data from several prominent RS segmentation and detection datasets: WHU, LoveDA, INRIA, and iSAID. We employ an innovative dual-track annotation generation pipeline. Firstly, we leverage Large Language Models (LLMs), specifically GPT-4.1, with meticulously designed prompts to automatically generate a suite of detailed annotations including image captions, spatial relations, and semantic tags, alongside complex caption-based VQA pairs. Secondly, to address the challenging task of object counting in RS imagery, we have developed a specialized automated process that extracts object counts directly from the original segmentation data; GPT-4.1 then formulates natural language answers from these counts, which are paired with preset question templates to create counting QA pairs. RSVLM-QA comprises 13,820 images and 162,373 VQA pairs, featuring extensive annotations and diverse question types. We provide a detailed statistical analysis of the dataset and a comparison with existing RS VQA benchmarks, highlighting the superior depth and breadth of RSVLM-QA's annotations. Furthermore, we conduct benchmark experiments on Six mainstream Vision Language Models (VLMs), demonstrating that RSVLM-QA effectively evaluates and challenges the understanding and reasoning abilities of current VLMs in the RS domain. We believe RSVLM-QA will serve as a pivotal resource for the RS VQA and VLM research communities, poised to catalyze advancements in the field. The dataset, generation code, and benchmark models are publicly available at https://github.com/StarZi0213/RSVLM-QA.

Large Language Models (LLMs) hold the potential for clinical task-shifting by processing unstructured clinical text, enabling tasks such as clinical concept extraction and medical question answering from electronic health records. If implemented reliably, such approaches may benefit over-burdened healthcare systems, particularly in resource-limited settings and for traditionally overlooked populations, provided that local fine-tuning is supported by appropriate clinical and technical expertise. However, this powerful technology remains largely understudied in real-world contexts, particularly in the Global South. This study aims to assess whether openly available LLMs can be used reliably for processing medical notes in real-world settings in South Asia. We used publicly available LLMs to parse de-identified clinical notes from a large electronic health records (EHR) database in Pakistan, containing hospital records for 8.2 million patients. ChatGPT (GPT-3.5) as a general-purpose LLM, and GatorTron (base), BioMegatron, BioBert and ClinicalBERT as medical LLMs were evaluated when applied to these data, after fine-tuning them with (a) publicly available clinical datasets namely Informatics for Integrating Biology & the Bedside (I2B2) and National NLP Clinical Challenges (N2C2) for medical concept extraction (MCE) and emrQA for medical question answering (MQA), and (b) the local Pakistani de-identified EHR dataset, which includes inpatient Discharge Summaries (DS) and Subjective, Objective, Assessment, and Plan (SOAP) notes, as detailed in this paper. MCE models were applied to these clinical notes using both 3-label and 9-label formats, while MQA models were applied to medical questions. Internal and external validation performance was measured for (a) and (b) using F1 score, precision, recall, and accuracy for MCE and BLEU and ROUGE-L, which measure lexical and sequence similarity, for MQA. When clinical LLMs were not fine-tuned on the local EHR dataset, their performance during external validation on local data was notably poorer compared to internal validation on the dataset used for fine-tuning, with reductions of at least 15% in F1 scores for MCE and 35% in ROUGE-L and BLEU scores for MQA tasks. This suggests potential bias and highlights the inability of the medical LLMs to reliably handle the data distribution of the local population without further fine-tuning and adaptation. This trend persisted across two distinct natural language processing tasks: concept extraction and question answering, spanning a spectrum of task complexities. However, fine-tuning the LLMs with local EHR data significantly improved model performance across both tasks, yielding a 7.5% to 15% increase in the F1 score for MCE and a 27% to 53% increase in ROUGE-L and BLEU scores for MQA. Notably, ChatGPT, as a general-purpose LLM, stood out as an exception, demonstrating superior performance across all measured metrics on the local dataset compared to the publicly available dataset, with improvements ranging from 3% to 17% on the local EHR dataset, even without fine-tuning on the local data. Publicly available LLMs, predominantly trained on data from high-income regions, were found to be unreliable when applied in a real-world clinical setting in Pakistan. Fine-tuning them with local EHR data and regional clinical contexts improved their reliability, demonstrating a feasible adaptation strategy that is substantially less resource-intensive than training large language models from scratch. Close collaboration between local clinical and technical experts to curate and leverage more representative, inclusive, and unbiased medical datasets, can play a crucial role in further ensuring reliability of LLMs for resource-limited, overburdened settings, to be used in ways that are safe, fair, and beneficial for all.

The remarkable achievements of ChatGPT and Generative Pre-trained Transformer 4 (GPT-4) have sparked a wave of interest and research in the field of large language models (LLMs) for artificial general intelligence (AGI). These models provide intelligent solutions that are closer to human thinking, enabling us to use general artificial intelligence (AI) to solve problems in various applications. However, in the field of remote sensing (RS), the scientific literature on the implementation of AGI remains relatively scant. Existing AI-related research in RS focuses primarily on visual-understanding tasks while neglecting the semantic understanding of the objects and their relationships. This is where vision-LMs (VLMs) excel as they enable reasoning about images and their associated textual descriptions, allowing for a deeper understanding of the underlying semantics. VLMs can go beyond visual recognition of RS images and can model semantic relationships as well as generate natural language descriptions of the image. This makes them better suited for tasks that require both visual and textual understanding, such as image captioning and visual question answering (VQA). This article provides a comprehensive review of the research on VLMs in RS, summarizing the latest progress, highlighting current challenges, and identifying potential research opportunities. Specifically, we review the application of VLMs in mainstream RS tasks, including image captioning, text-based image generation, text-based image retrieval (TBIR), VQA, scene classification, semantic segmentation, and object detection. For each task, we analyze representative works and discuss research progress. Finally, we summarize the limitations of existing works and provide possible directions for future development. This review aims to provide a comprehensive overview of the current research progress of VLMs in RS (see Figure 1), and to inspire further research in this exciting and promising field.

Interacting with Large Language Models (LLMs) via declarative queries is increasingly popular for tasks like question answering and data extraction, thanks to their ability to process vast unstructured data. However, LLMs often struggle with answering complex factual questions, exhibiting low precision and recall in the returned data. This challenge highlights that executing queries on LLMs remains a largely unexplored domain, where traditional data processing assumptions often fall short. Conventional query optimization, typically cost-driven, overlooks LLM-specific quality challenges such as contextual understanding. Just as new physical operators are designed to address the unique characteristics of LLMs, optimization must consider these quality challenges. Our results highlight that adhering strictly to conventional query optimization principles fails to generate the best plans in terms of result quality. To tackle this challenge, we present a novel approach to enhance SQL results by applying query optimization techniques specifically adapted for LLMs. We introduce a database system, GALOIS, that sits between the query and the LLM, effectively using the latter as a storage layer. We design alternative physical operators tailored for LLM-based query execution and adapt traditional optimization strategies to this novel context. For example, while pushing down operators in the query plan reduces execution cost (fewer calls to the model), it might complicate the call to the LLM and deteriorate result quality. Additionally, these models lack a traditional catalog for optimization, leading us to develop methods to dynamically gather such metadata during query execution. Our solution is compatible with any LLM and balances the trade-off between query result quality and execution cost. Experiments show up to 144% quality improvement over questions in Natural Language and 29% over direct SQL execution, highlighting the advantages of integrating database solutions with LLMs.

Large language models (LLMs) have shown impressive capabilities across various natural language tasks. However, evaluating their alignment with human preferences remains a challenge. To this end, we propose a comprehensive human evaluation framework to assess LLMs’ proficiency in following instructions on diverse real-world tasks. We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and in-depth manner. We also design detailed evaluation standards and processes to facilitate consistent, unbiased judgments from human evaluators. A test set of over 3,000 instances is released, spanning different difficulty levels and knowledge domains. Our work provides a standardized methodology to evaluate human alignment in LLMs for both English and Chinese. We also analyze the feasibility of automating parts of evaluation with a strong LLM (GPT-4). Our framework supports a thorough assessment of LLMs as they are integrated into real-world applications. We have made publicly available the task tree, TencentLLMEval dataset, and evaluation methodology which have been demonstrated as effective in assessing the performance of Tencent Hunyuan LLMs 1 . By doing so, we aim to facilitate the benchmarking of advances in the development of safe and human-aligned LLMs.

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora.These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions.In this paper, we compare seven public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering (QA) tasks.For instance, across the tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 12.1% of cases, reach a (statistical) tie in 49.8% of cases, and are significantly worse than their base models in the remaining 38.2% of cases.Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately; and (iii) accounting for statistical uncertainty in comparisons.While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions.Our findings suggest that state-of-the-art generaldomain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.

Newly available optical satellite images with 1‐m ground resolution such as IKONOS mean that rapid postdisaster damage assessment might be made over large areas. Such surveys could be of great value to emergency management and post‐event recovery operations and have particular promise for earthquake areas, where damage distribution is often very uneven. In this paper three satellite images taken before and after the 26 January 2001 Gujarat earthquake were studied for damage assessment purposes. The images comprised a post‐earthquake cover of the city of Bhuj, which was close to the epicenter, and pre‐ and post‐earthquake cover of the city Ahmedabad. The assessment data was then compared with damage surveys actually made on‐site. Three separate experiments were conducted. In the first, the satellite image of Bhuj was compared with detailed ground photos of 28 severely damaged buildings taken at about the same time as the satellite image, to investigate the levels and types of damage that can and cannot be identified. In the second experiment, the whole city center of Bhuj was damage mapped using only the satellite image. This was subsequently compared with a map produced from a building‐by‐building damage survey. In the third experiment, pre‐ and post‐earthquake images for a large area of Ahmedabad were compared and totally collapsed buildings were identified. These sites were subsequently visited to confirm the accuracy of the observations. The experiment results indicate that rapid visual screening can identify areas of heavy damage and individual collapsed buildings, even when comparative cover does not exist. The need to develop a tool with direct application to support emergency response is discussed.

PurposeCurrent benchmarks evaluating large language models (LLMs) in ophthalmology are narrow and disproportionately prioritize accuracy. We introduce BEnchmarking LLMs for Ophthalmology (BELO), a standardized evaluation benchmark developed through multiple rounds of expert checking by 13 ophthalmologists. BEnchmarking LLMs for Ophthalmology assesses ophthalmology-related knowledge and reasoning quality.SubjectsThis study did not involve human participation.DesignCross-sectional study.MethodsUsing keyword matching and a fine-tuned PubMed Bidirectional Encoder Representations from Transformers model, we curated ophthalmology-specific multiple-choice questions (MCQs) from diverse medical data sets (Basic and Clinical Science Course [BCSC], Multi-Subject Multi-Choice Dataset for Medical domain [MedMCQA], Medical Question Answering [MedQA], Biomedical Semantic Indexing and Question Answering [BioASQ], and PubMed Question Answering [PubMedQA]). The data set underwent multiple rounds of expert checking. Duplicate and substandard questions were systematically removed. Ten ophthalmologists refined the explanations of each MCQ's correct answer. This was further adjudicated by 3 senior ophthalmologists. To illustrate BELO's utility, we evaluated 8 LLMs (OpenAI o1, o3-mini, GPT-5, GPT-4o, DeepSeek-R1, MedGemma-4B, Llama-3-8B, and Gemini 1.5 Pro).Main Outcome MeasuresThe 8 LLMs were evaluated in terms using accuracy, macro-F1, and 5 text-generation metrics (Recall-Oriented Understudy for Gisting Evaluation, BERTScore, BARTScore, Metric for Evaluation of Translation with Explicit Ordering, and AlignScore). In a further evaluation involving human experts, 2 ophthalmologists qualitatively reviewed 50 randomly selected outputs for accuracy, comprehensiveness, and completeness.ResultsBEnchmarking LLMs for Ophthalmology consists of 900 high-quality, expert-reviewed questions aggregated from 5 sources: BCSC (260), BioASQ (10), MedMCQA (572), MedQA (40), and PubMedQA (18). To demonstrate BELO's utility, we conducted a series of benchmarking exercises. In the quantitative evaluation, GPT-5 achieved the highest accuracy (0.90, 95% confidence interval [CI]: 0.89–0.92) and macro-F1 score (0.91, 95% CI: 0.89–0.93). On the other hand, the models' performance on text-generation metrics varied and were generally suboptimal, with scores ranging from 20.4 to 72.0 (out of 100, excluding the BARTScore metric), indicating room for improvement in clinical reasoning. In expert evaluations, GPT-4o was rated highest for accuracy and readability, while Gemini 1.5 Pro scored highest for completeness. A public leaderboard has been established to promote transparent evaluation and reporting. Importantly, the BELO data set will remain a hold-out, evaluation-only benchmark to ensure fair and reproducible comparisons of future models.ConclusionsBEnchmarking LLMs for Ophthalmology provides a robust clinically relevant benchmark for evaluating both the accuracy and reasoning capabilities of current and emerging LLMs in ophthalmology. Future BELO benchmarking efforts will expand to include vision-based question answering and clinical scenario management tasks.Financial Disclosure(s)The authors have no proprietary or commercial interest in any materials discussed in this article.

Large Language Models (LLMs) recently demonstrated extraordinary capability, including natural language processing (NLP), language translation, text generation, question answering, etc. Moreover, LLMs are a new and essential part of computerized language processing, having the ability to understand complex verbal patterns and generate coherent and appropriate replies for the situation. Though this success of LLMs has prompted a substantial increase in research contributions, rapid growth has made it difficult to understand the overall impact of these improvements. Since a lot of new research on LLMs is coming out quickly, it is getting tough to get an overview of all of them in a short note. Consequently, the research community would benefit from a short but thorough review of the recent changes in this area. This article thoroughly overviews LLMs, including their history, architectures, transformers, resources, training methods, applications, impacts, challenges, etc. This paper begins by discussing the fundamental concepts of LLMs with its traditional pipeline of the LLMs training phase. It then provides an overview of the existing works, the history of LLMs, their evolution over time, the architecture of transformers in LLMs, the different resources of LLMs, and the different training methods that have been used to train them. It also demonstrated the datasets utilized in the studies. After that, the paper discusses the wide range of applications of LLMs, including biomedical and healthcare, education, social, business, and agriculture. It also illustrates how LLMs create an impact on society and shape the future of AI and how they can be used to solve real-world problems. Then it also explores open issues and challenges to deploying LLMs in real-world scenario. Our review paper aims to help practitioners, researchers, and experts thoroughly understand the evolution of LLMs, pre-trained architectures, applications, challenges, and future goals.