ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation

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.

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.

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.

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.

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.

Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications. Large Language Models (LLMs) have demonstrated impressive capabilities by advancing state-of-the-art on many language-based benchmarks. Their ability to process and understand natural language open exciting possibilities in various domains. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with LLMs remains an understudied problem that has recently gained more attention.This tutorial builds upon recent advances in expressing reasoning problems through the lens of tasks on graph data. The first part of the tutorial will provide an in-depth discussion of techniques for representing graphs as inputs to LLMs. The second, hands-on, portion will demonstrate these techniques in a practical setting. As a learning outcome of participating in the tutorial, participants will be able to analyze graphs either on free-tier Colab or their local machines with the help of LLMs.

BackgroundIn recent years, large language models (LLMs) have shown promise in various domains, notably in biomedical sciences. However, their real-world application is often limited by issues like erroneous outputs and hallucinatory responses.ResultsWe developed the knowledge graph–based thought (KGT) framework, an innovative solution that integrates LLMs with knowledge graphs (KGs) to improve their initial responses by utilizing verifiable information from KGs, thus significantly reducing factual errors in reasoning. The KGT framework demonstrates strong adaptability and performs well across various open-source LLMs. Notably, KGT can facilitate the discovery of new uses for existing drugs through potential drug–cancer associations and can assist in predicting resistance by analyzing relevant biomarkers and genetic mechanisms. To evaluate the knowledge graph question answering task within biomedicine, we utilize a pan-cancer knowledge graph to develop a pan-cancer question answering benchmark, named pan-cancer question answering.ConclusionsThe KGT framework substantially improves the accuracy and utility of LLMs in the biomedical field. This study serves as a proof of concept, demonstrating its exceptional performance in biomedical question answering.

Extracting information from unstructured and semi-structured geoscience literature is a crucial step in conducting geological research. The traditional machine learning extraction paradigm requires a substantial amount of high-quality manually annotated data for model training, which is time-consuming, labor-intensive, and not easily transferable to new fields. Recently, large language models (LLMs) (e.g., ChatGPT, GPT-4, and LLaMA), have shown great performance in various natural language processing (NLP) tasks, such as question answering, machine translation, and text generation. A substantial body of work has demonstrated that LLMs possess strong in-context learning (ICL) and even zero-shot learning capabilities to solve downstream tasks without specifically designed supervised fine-tuning. In this paper, we propose utilizing LLMs for geoscience literature information extraction. Specifically, we design a hierarchical PDF parsing pipeline and an automated knowledge extraction process, which can significantly reduce the need for manual data annotation, assisting geoscientists in literature data mining. For the hierarchical PDF parsing pipeline, firstly, a document layout detection model fine-tuned on geoscience literature is employed for layout detection, obtaining layout detection information for the document. Secondly, based on the document layout information, an optical character content parsing model is used for content parsing, obtaining the text structure and plain text corresponding to the content. Finally, the text structure and plain text are combined and reconstructed to ultimately obtain the parsed structured data. For the automated knowledge extraction process, firstly, the parsed long text is segmented into paragraphs to adapt to the input length limit of LLMs. Subsequently, a few-shot prompting method is employed for structured knowledge extraction, encompassing two tasks: attribute value extraction and triplet extraction. In attribute value extraction, prompts are generated automatically by the LLMs based on the subdomain and attribute names, facilitating the location and extraction of values related to subdomain attribute names in the text. For triplet extraction, the LLMs employ a procedural approach to entity extraction, entity type extraction, and relation extraction, following the knowledge graph structure pattern. Finally, the extracted structured knowledge is stored in the form of knowledge graphs, facilitating further analysis and integration of various types of knowledge from the literature. Our proposed approach turns out to be simple, flexible, and highly effective in geoscience literature information extraction. Demonstrations of information extraction in subdomains such as radiolarian fossils and fluvial facies have yielded satisfactory results. The extraction efficiency has significantly improved, and feedback from domain experts indicates a relatively high level of accuracy in the extraction process. The extracted results can be used to construct a foundational knowledge graph for geoscience literature, supporting the comprehensive construction and efficient application of a geoscience knowledge graph.

Large language models (LLMs) have recently shown impressive zero-shot capabilities, whereby they can use auxiliary data, without the availability of task-specific training examples, to complete a variety of natural language tasks, such as summarization, dialogue generation, and question answering. However, despite many promising applications of LLMs in clinical medicine, adoption of these models has been limited by their tendency to generate incorrect and sometimes even harmful statements. We tasked a panel of eight board-certified clinicians and two health care practitioners with evaluating Almanac, an LLM framework augmented with retrieval capabilities from curated medical resources for medical guideline and treatment recommendations. The panel compared responses from Almanac and standard LLMs (ChatGPT-4, Bing, and Bard) versus a novel data set of 314 clinical questions spanning nine medical specialties. Almanac showed a significant improvement in performance compared with the standard LLMs across axes of factuality, completeness, user preference, and adversarial safety. Our results show the potential for LLMs with access to domain-specific corpora to be effective in clinical decision-making. The findings also underscore the importance of carefully testing LLMs before deployment to mitigate their shortcomings. (Funded by the National Institutes of Health, National Heart, Lung, and Blood Institute.).

Structure reasoning is a fundamental capability of large language models (LLMs), enabling them to reason about structured commonsense and answer multi-hop questions. However, existing benchmarks for structure reasoning mainly focus on horizontal and coordinate structures (e.g. graphs), overlooking the hierarchical relationships within them. Hierarchical structure reasoning is crucial for human cognition, particularly in memory organization and problem-solving. It also plays a key role in various real-world tasks, such as information extraction and decision-making. To address this gap, we propose HiBench, the first framework designed to systematically benchmark the hierarchical reasoning capabilities of LLMs from initial structure generation to final proficiency assessment. It encompasses six representative scenarios, covering both fundamental and practical aspects, and consists of 30 tasks with varying hierarchical complexity, totaling 39,519 queries. To evaluate LLMs comprehensively, we develop five capability dimensions that depict different facets of hierarchical structure understanding. Through extensive evaluation of 20 LLMs from 10 model families, we reveal key insights into their capabilities and limitations: 1) existing LLMs show proficiency in basic hierarchical reasoning tasks; 2) they still struggle with more complex structures and implicit hierarchical representations, especially in structural modification and textual reasoning. Based on these findings, we create a small yet well-designed instruction dataset, which enhances LLMs' performance on HiBench by an average of 88.84% (Llama-3.1-8B) and 31.38% (Qwen2.5-7B) across all tasks. The HiBench dataset and toolkit are available at https://github.com/jzzzzh/HiBench to encourage evaluation.

The rapid advancement of large language models (LLMs) has opened up promising opportunities for their downstream applications in question-answering (QA), such as ChatGPT, ChatGLM, etc. However, such LLMs do not perform very well in domain-specific QA tasks without fine-tuning. But directly fine-tuning LLMs on domain-specific corpus data may lead to catastrophic forgetting, causing the LLMs to lose their general language capability. To address this problem, we propose the Knowledge-Enhanced Fine-Tuning (KEFT) method, an unsupervised fine-tuning approach to enhance the knowledge capability of LLMs in domain-specific QA tasks while preserving their general language capability. KEFT leverages the inherent language comprehension of pre-trained LLMs to generate synthetic-QA datasets from domain-specific corpus data autonomously for fine-tuning, and adopts a Low-Rank Adaptation (LoRA) method to further alleviate over-fitting. Furthermore, to enhance the representation of domain-specific knowledge, we introduce a knowledge-enhanced fine-tuning loss function, which encourages the model to learn the knowledge-question connection, thereby generating natural and knowledgeable answers. Our evaluations across multiple domain-specific datasets demonstrate that KEFT surpasses state-of-the-art fine-tuning approaches, enhancing the performance of various LLMs in QA tasks in both English and Chinese languages.

Refusal-Aware Instruction Tuning (RAIT) enables Large Language Models (LLMs) to refuse to answer unknown questions. By modifying responses of unknown questions in the training data to refusal responses such as ''I don't know", RAIT enhances the reliability of LLMs and reduces their hallucination. Generally, RAIT modifies training samples based on the correctness of the initial LLM's response. However, this crude approach can cause LLMs to excessively refuse answering questions they could have correctly answered, the problem we call over-refusal. In this paper, we explore two primary causes of over-refusal: Static conflict occurs when similar samples within the LLM’s feature space receive differing supervision signals (original vs. modified ''I don't know"). Dynamic conflict arises as the LLM's evolving knowledge during SFT enables it to answer previously unanswerable questions, but the now-answerable training samples still retain the original ''I don't know" supervision signals from the initial LLM state, leading to inconsistencies. These conflicts cause the trained LLM to misclassify known questions as unknown, resulting in over-refusal. To address this issue, we introduce Certainty Represented Knowledge Flow for Refusal-Aware Instructions Tuning (CRaFT). CRaFT centers on two main contributions: First, we additionally incorporate response certainty to selectively filter and modify data, reducing static conflicts. Second, we implement preliminary rehearsal training to characterize changes in the LLM's knowledge state, which helps mitigate dynamic conflicts during the fine-tuning process. We conducted extensive experiments on open-ended question answering and multiple-choice question task. Experiment results show that CRaFT can improve LLM's overall performance during the RAIT process.

Abstract. Large language models (LLMs) have revolutionized the field of natural language processing (NLP), demonstrating remarkable capabilities in understanding, generating, and manipulating human language. This comprehensive review explores the development, applications, optimizations, and challenges of LLMs. This paper begin by tracing the evolution of these models and their foundational architectures, such as the Transformer, GPT, and BERT. We then delve into the applications of LLMs in natural language understanding tasks, including sentiment analysis, named entity recognition, question answering, and text summarization, highlighting real-world use cases. Next, we examine the role of LLMs in natural language generation, covering areas such as content creation, language translation, personalized recommendations, and automated responses. We further discuss LLM applications in other NLP tasks like text style transfer, text correction, and language model pre-training. Subsequently, we explore techniques for optimizing and improving LLMs, including model compression, explainability, robustness, and security. Finally, we address the challenges posed by the significant computational requirements, sample inefficiency, and ethical considerations surrounding LLMs. We conclude by discussing potential future research directions, such as efficient architectures, few-shot learning, bias mitigation, and privacy-preserving techniques, which will shape the ongoing development and responsible deployment of LLMs in NLP.

Despite growing interest in the use of Large Language Models (LLMs) in agriculture, their integration into Extension and Advisory Services (EAS) remains underexamined. This review applies Rogers’ Diffusion of Innovation theory alongside Wüstenhagen et al.’s Social Acceptance Framework to assess current LLM applications, challenges, and contextual factors influencing their acceptance within EAS. Following a rapid review using the PRISMA framework, 12 studies were thematically analyzed first manually and then using NVivo 14. Results show that LLMs support functions such as question answering, climate analytics, and pest identification, offering innovative agronomic insights but potentially disrupting traditional EAS roles. Most LLM development is led by private firms, raising concerns about transparency, accountability, and inclusion. EAS practitioners are uniquely positioned to promote responsible LLM adoption by leveraging local knowledge and trusted relationships, though this requires targeted capacity development initiatives and inclusive strategies. This review contributes to a broader understanding of how frameworks for responsible innovation and social acceptance can inform the adoption of AI in agriculture.