Large Language Models: A Survey

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

1. Très proche Article de revue Pas pertinent

   A Comprehensive Overview of Large Language Models (LLMs)

   M. Uysal, Aynur Uysal, Yasemin Karagül · 2025 · International Journal For Multidisciplinary Research · cité 9 fois · Pas encore résumé

   «A Comprehensive Overview» passe en revue les architectures, l’entraînement, les applications et les limites des LLM, comme cette synthèse générale.

   Résumé scientifique

   Large Language Models (LLMs) have revolutionized natural language processing (NLP) by leveraging deep learning to generate human-like text. These models, including GPT, BERT, and their variants, have found applications in diverse fields such as healthcare, education, and finance. This paper explores the architecture, training process, applications, and limitations of LLMs, providing an example implementation and visualization of a key NLP task.

2. Très proche Même question Pas pertinent

   A Survey of Large Language Models for European Languages

   Wazir Ali, Sampo Pyysalo · 2024 · arXiv.org · preprint, non relu par les pairs · cité 11 fois · Pas encore résumé

   «A Survey of Large Language Models for European Languages» examine les familles et les méthodes des LLM, en ciblant les langues officielles de l’Union européenne.

   Résumé scientifique

   Large Language Models (LLMs) have gained significant attention due to their high performance on a wide range of natural language tasks since the release of ChatGPT. The LLMs learn to understand and generate language by training billions of model parameters on vast volumes of text data. Despite being a relatively new field, LLM research is rapidly advancing in various directions. In this paper, we present an overview of LLM families, including LLaMA, PaLM, GPT, and MoE, and the methods developed to create and enhance LLMs for official European Union (EU) languages. We provide a comprehensive summary of common monolingual and multilingual datasets used for pretraining large language models.

3. Très proche Base de cet article Cité par cet article Pas pertinent

   A Survey of Large Language Models

   Wayne Xin Zhao, Kun Zhou, Junyi Li et al. · 2023 · Computation and Language · cité 5 220 fois · Résumé IA disponible

   «A Survey of Large Language Models» retrace l’évolution des modèles de langue jusqu’aux modèles préentraînés, et cet article le cite.

   Résumé scientifique

   Language is essentially a complex, intricate system of human expressions governed by grammatical rules. It poses a significant challenge to develop capable AI algorithms for comprehending and grasping a language. As a major approach, language modeling has been widely studied for language understanding and generation in the past two decades, evolving from statistical language models to neural language models. Recently, pre-trained language models (PLMs) have been proposed by pre-training Transformer models over large-scale corpora, showing strong capabilities in solving various NLP tasks. Since researchers have found that model scaling can lead to performance improvement, they further study t…

4. Très proche Article de revue Pas pertinent

   Large language models in machine learning

   Goutam Saha · 2024 · International Journal of Applied Research on Information Technology and Computing · Pas encore résumé

   «Large language models in machine learning» synthétise les architectures, l’entraînement, l’évaluation et les défis des LLM.

   Résumé scientifique

   AbstractIn recent years, large language models (LLMs) have revolutionized the field of machine learning (ML), demonstrating unprecedented capabilities in natural language processing (NLP) tasks. This review provides an in-depth analysis of the evolution, architectural innovations, training techniques, applications, evaluation metrics, and challenges associated with LLMs. By exploring both the advancements and the limitations of current LLMs, this paper aims to offer insights into the future directions for research and development in this dynamic field.

5. Très proche Même question Pas pertinent

   The Evolution Of Large Language Models: A Comparative Survey Of Leading Approaches

   Nirali Arora, Jaya Gupta, P. Patil et al. · 2025 · International Journal of Environmental Science · Pas encore résumé

   «The Evolution Of Large Language Models» compare des modèles récents selon leur architecture, leurs données d’entraînement, leurs performances et leurs applications.

   Résumé scientifique

   The exponential development of Large Language Models (LLMs) has significantly contributed to the evolution of the artificial intelligence (AI) landscape. This paper focuses on surveying several state-of-the-art LLMs, including big names in the industry like, OpenAI's GPT-4, Anthropic's Claude 3, Google's PaLM 2, and Meta's LLaMA 3.1. We evaluated these models based on their architecture, training data, performance and applications, using information from official papers, technical documentation and third-party reviews. By combining the claims from primary sources and third-party analysis, this survey hopes to give a summary of what the latest LLMs can do, what they can’t and what’s next for …

6. Très proche Article de revue Pas pertinent

   A Comprehensive Overview of Large Language Models

   Humza Naveed, Asad Ullah Khan, Shi Qiu et al. · 2023 · Computation and Language · cité 2 129 fois · Résumé IA disponible

   «A Comprehensive Overview» classe les architectures de LLM et examine entraînement, jeux de données et évaluations.

   Résumé scientifique

   Large Language Models (LLMs) have shown excellent generalization capabilities that have led to the development of numerous models. These models propose various new architectures, tweaking existing architectures with refined training strategies, increasing context length, using high-quality training data, and increasing training time to outperform baselines. Analyzing new developments is crucial for identifying changes that enhance training stability and improve generalization in LLMs. This survey paper comprehensively analyses the LLMs architectures and their categorization, training strategies, training datasets, and performance evaluations and discusses future research directions. Moreover…

7. Très proche Article de revue Pas pertinent

   Large language models (LLMs): survey, technical frameworks, and future challenges

   Pranjal Kumar · 2024 · Artificial Intelligence Review · cité 389 fois · Pas encore résumé

   «Large language models (LLMs)» présente les cadres techniques, les applications variées et les défis des LLM.

   Résumé scientifique

   Artificial intelligence (AI) has significantly impacted various fields. Large language models (LLMs) like GPT-4, BARD, PaLM, Megatron-Turing NLG, Jurassic-1 Jumbo etc., have contributed to our understanding and application of AI in these domains, along with natural language processing (NLP) techniques. This work provides a comprehensive overview of LLMs in the context of language modeling, word embeddings, and deep learning. It examines the application of LLMs in diverse fields including text generation, vision-language models, personalized learning, biomedicine, and code generation. The paper offers a detailed introduction and background on LLMs, facilitating a clear understanding of their …

8. Très proche Même question Pas pertinent

   Large Language Models for NLP: An In-Depth Comparative Examination

   Zakaria Alomari, Ojasvi Sharma, Shivam Sawarn et al. · 2025 · International Conference on Multimodal Interaction · cité 1 fois · Pas encore résumé

   «Large Language Models for NLP» compare six modèles sur leurs performances, leurs tailles, leurs méthodes d’entraînement et leurs fonctionnalités.

   Résumé scientifique

   The discipline of Large Language Models (LLMs) is rapidly advancing, and it is essential to explore their capabilities and limitations for further development. This study conducts a comparative analysis of six prominent models: GPT-4, LLaMA 2, FALCON, BLOOM, LaMDA and DeepSeek. By evaluating their performance across a range of tasks and benchmarks, including model size, training methodologies, and unique functionalities, we aim to identify the current state-of-the-art and propose directions for future research. Through this examination, we seek to enhance the understanding of LLMs and contribute to their responsible and efficient deployment.

Les travaux antérieurs sur lesquels il s’appuie

1. Très proche Même question Pas pertinent

   A Survey on Evaluation of Large Language Models

   Yupeng Chang, Xu Wang, Jindong Wang et al. · 2023 · Computation and Language · cité 4 007 fois · Résumé IA disponible

   «A Survey on Evaluation» se concentre sur les méthodes d’évaluation des LLM, tandis que cet article traite aussi des métriques et benchmarks.

   Résumé scientifique

   Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the …

2. Très proche Contexte plus large Pas pertinent

   Challenges and Applications of Large Language Models

   Jean Kaddour, J. Harris, Maximilian Mozes et al. · 2023 · arXiv.org · preprint, non relu par les pairs · cité 528 fois · Pas encore résumé

   «Challenges and Applications» recense les problèmes ouverts et les applications des LLM, deux thèmes abordés dans cette synthèse.

   Résumé scientifique

   Large Language Models (LLMs) went from non-existent to ubiquitous in the machine learning discourse within a few years. Due to the fast pace of the field, it is difficult to identify the remaining challenges and already fruitful application areas. In this paper, we aim to establish a systematic set of open problems and application successes so that ML researchers can comprehend the field's current state more quickly and become productive.

3. Très proche Contexte plus large Pas pertinent

   TrustLLM: Trustworthiness in Large Language Models

   Li-Chao Sun, Yue Huang, Haoran Wang et al. · 2024 · arXiv.org · preprint, non relu par les pairs · cité 383 fois · Résumé IA disponible

   «TrustLLM» étudie la fiabilité des LLM au moyen de principes, de benchmarks et d’analyses, un enjeu spécialisé de leur évaluation.

   Résumé scientifique

   Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span …

4. Très proche Autre approche du problème Pas pertinent

   Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

   Baolin Peng, Michel Galley, Pengcheng He et al. · 2023 · Computation and Language · preprint, non relu par les pairs · cité 562 fois · Résumé IA disponible

   «Check Your Facts and Try Again» augmente un LLM avec des connaissances externes et des retours automatisés pour limiter les hallucinations.

   Résumé scientifique

   Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and inability to use external knowledge.This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in consolidated external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by util…

5. Très proche Contexte plus large Pas pertinent

   Unifying Large Language Models and Knowledge Graphs: A Roadmap

   Shirui Pan, Linhao Luo, Yufei Wang et al. · 2023 · IEEE Transactions on Knowledge and Data Engineering · cité 1 932 fois · Résumé IA disponible

   «Unifying Large Language Models and Knowledge Graphs» propose une feuille de route pour associer les LLM aux graphes de connaissances.

   Résumé scientifique

   Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia, and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolve by nature, which challenges the existing methods in KGs to generate new facts and represent unseen kno…

Les articles qui le citent

1. Très proche Prolonge cet article Pas pertinent

   Security and Privacy Challenges of Large Language Models: A Survey

   Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu · 2025 · ACM Computing Surveys · cité 370 fois · Résumé IA disponible

   «Security and Privacy Challenges» cite cette synthèse et examine les attaques de sécurité et de confidentialité visant les LLM.

   Résumé scientifique

   Large language models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Today, LLMs have become quite popular tools in natural language processing tasks, with the capability to analyze complicated linguistic patterns and provide relevant responses depending on the context. While offering significant advantages, these models are also vulnerable to security and privacy attacks, such as jailbreaking attacks, data poisoning attacks, and personally identifiable information leakage attacks. This survey provides a thorough review of the security and privacy challenges of LLMs…

2. Très proche Prolonge cet article Pas pertinent

   Large Language Model Architectures and Their Trade-offs in Efficiency and Understanding

   Jing-Yang Guo · 2026 · Advances in Engineering Technology Research · Pas encore résumé

   «Large Language Model Architectures and Their Trade-offs» cite cette synthèse et analyse les compromis entre efficacité et compréhension des architectures.

   Résumé scientifique

   As an important trend in the development of artificial intelligence, the large language model (LLM) is committed to building a two-way human-computer interaction, which has excellent performance in dialogue, real-time feedback, task execution, and so on. Research LLM architectures and their trade-offs in efficiency and understanding. Based on the references, this paper summarizes the basic theoretical framework of LLM technology, including its definition, key features, development history, and core technologies. Then, the existing literature is quantitatively analyzed, and the research hotspots of LLM technology are analyzed by using Citespace bibliometric tools. Based on the LLM, this paper…

3. Très proche Prolonge cet article Pas pertinent

   Datasets for Large Language Models: A Comprehensive Survey

   Yang Liu, Jiahuan Cao, Chongyu Liu et al. · 2024 · arXiv.org · preprint, non relu par les pairs · cité 149 fois · Résumé IA disponible

   «Datasets for Large Language Models» cite cette synthèse et se concentre sur la catégorisation des jeux de données pour les LLM.

   Résumé scientifique

   This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that sustains and nurtures the development of LLMs. Consequently, examination of these datasets emerges as a critical topic in research. In order to address the current lack of a comprehensive overview and thorough analysis of LLM datasets, and to gain insights into their current status and future trends, this survey consolidates and categorizes the fundamental aspects of LLM datasets from five perspectives: (1) Pre-training Corpora; (2) Instruction Fine-tuning Data…

4. Très proche Prolonge cet article Pas pertinent

   On protecting the data privacy of Large Language Models (LLMs) and LLM agents: A literature review

   Biwei Yan, Kun Li, Minghui Xu et al. · 2025 · High-Confidence Computing · cité 85 fois · Pas encore résumé

   «On protecting the data privacy» cite cette synthèse et passe en revue les risques de fuite d’informations dans les LLM et leurs agents.

   Résumé scientifique

   Large Language Models (LLMs) are complex artificial intelligence systems, which can understand, generate, and translate human languages. By analyzing large amounts of textual data, these models learn language patterns to perform tasks such as writing, conversation, and summarization. Agents built on LLMs (LLM agents) further extend these capabilities, allowing them to process user interactions and perform complex operations in diverse task environments. However, during the processing and generation of massive data, LLMs and LLM agents pose a risk of sensitive information leakage, potentially threatening data privacy. This paper aims to demonstrate data privacy issues associated with LLMs and…

5. Très proche Prolonge cet article Pas pertinent

   Roles and potential of Large language models in healthcare: A comprehensive review

   Chi‐Hung Lin, Chang‐Fu Kuo · 2025 · Biomedical Journal · cité 102 fois · Pas encore résumé

   «Roles and potential of Large language models in healthcare» cite cette synthèse et examine les usages des LLM dans les soins.

   Résumé scientifique

   Large Language Models (LLMs) are capable of transforming healthcare by demonstrating remarkable capabilities in language understanding and generation. They have matched or surpassed human performance in standardized medical examinations and assisted in diagnostics across specialties like dermatology, radiology, and ophthalmology. LLMs can enhance patient education by providing accurate, readable, and empathetic responses, and they can streamline clinical workflows through efficient information extraction from unstructured data such as clinical notes. Integrating LLM into clinical practice involves user interface design, clinician training, and effective collaboration between Artificial Intel…