Large Language Models for Chatbot Health Advice Studies DOI Creative Commons
Bright Huo,

Amy Boyle,

Nana Marfo

и другие.

JAMA Network Open, Год журнала: 2025, Номер 8(2), С. e2457879 - e2457879

Опубликована: Фев. 4, 2025

Importance There is much interest in the clinical integration of large language models (LLMs) health care. Many studies have assessed ability LLMs to provide advice, but quality their reporting uncertain. Objective To perform a systematic review examine variability among peer-reviewed evaluating performance generative artificial intelligence (AI)–driven chatbots for summarizing evidence and providing advice inform development Chatbot Assessment Reporting Tool (CHART). Evidence Review A search MEDLINE via Ovid, Embase Elsevier, Web Science from inception October 27, 2023, was conducted with help sciences librarian yield 7752 articles. Two reviewers screened articles by title abstract followed full-text identify primary accuracy AI-driven (chatbot studies). then performed data extraction 137 eligible studies. Findings total were included. Studies examined topics surgery (55 [40.1%]), medicine (51 [37.2%]), care (13 [9.5%]). focused on treatment (91 [66.4%]), diagnosis (60 [43.8%]), or disease prevention (29 [21.2%]). Most (136 [99.3%]) evaluated inaccessible, closed-source did not enough information version LLM under evaluation. All lacked sufficient description characteristics, including temperature, token length, fine-tuning availability, layers, other details. describe prompt engineering phase study. The date querying reported 54 (39.4%) (89 [65.0%]) used subjective means define successful chatbot, while less than one-third addressed ethical, regulatory, patient safety implications LLMs. Conclusions Relevance In this chatbot studies, heterogeneous may CHART standards. Ethical, considerations are crucial as grows

Язык: Английский

A survey on large language model based autonomous agents DOI Creative Commons
Lei Wang, Chen Ma, Xueyang Feng

и другие.

Frontiers of Computer Science, Год журнала: 2024, Номер 18(6)

Опубликована: Март 22, 2024

Abstract Autonomous agents have long been a research focus in academic and industry communities. Previous often focuses on training with limited knowledge within isolated environments, which diverges significantly from human learning processes, makes the hard to achieve human-like decisions. Recently, through acquisition of vast amounts Web knowledge, large language models (LLMs) shown potential human-level intelligence, leading surge LLM-based autonomous agents. In this paper, we present comprehensive survey these studies, delivering systematic review holistic perspective. We first discuss construction agents, proposing unified framework that encompasses much previous work. Then, overview diverse applications social science, natural engineering. Finally, delve into evaluation strategies commonly used for Based also several challenges future directions field.

Язык: Английский

Процитировано

225
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly DOI Creative Commons
Yifan Yao, Jinhao Duan, Kaidi Xu

и другие.

High-Confidence Computing, Год журнала: 2024, Номер 4(2), С. 100211 - 100211

Опубликована: Март 1, 2024

Язык: Английский

Процитировано

222
Adapted large language models can outperform medical experts in clinical text summarization DOI
Dave Van Veen, Cara Van Uden, Louis Blankemeier

и другие.

Nature Medicine, Год журнала: 2024, Номер 30(4), С. 1134 - 1142

Опубликована: Фев. 27, 2024

Язык: Английский

Процитировано

163
A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges DOI Creative Commons
Mohaimenul Azam Khan Raiaan, Md. Saddam Hossain Mukta, Kaniz Fatema

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 26839 - 26874

Опубликована: Янв. 1, 2024

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

Язык: Английский

Процитировано

129
A survey of GPT-3 family large language models including ChatGPT and GPT-4 DOI Creative Commons

Katikapalli Subramanyam Kalyan

Natural Language Processing Journal, Год журнала: 2023, Номер 6, С. 100048 - 100048

Опубликована: Дек. 19, 2023

Large language models (LLMs) are a special class of pretrained (PLMs) obtained by scaling model size, pretraining corpus and computation. LLMs, because their large size on volumes text data, exhibit abilities which allow them to achieve remarkable performances without any task-specific training in many the natural processing tasks. The era LLMs started with OpenAI's GPT-3 model, popularity has increased exponentially after introduction like ChatGPT GPT4. We refer its successor OpenAI models, including GPT4, as family (GLLMs). With ever-rising GLLMs, especially research community, there is strong need for comprehensive survey summarizes recent progress multiple dimensions can guide community insightful future directions. start paper foundation concepts transformers, transfer learning, self-supervised models. then present brief overview GLLMs discuss various downstream tasks, specific domains languages. also data labelling augmentation robustness effectiveness evaluators, finally, conclude To summarize, this will serve good resource both academic industry people stay updated latest related GLLMs.

Язык: Английский

Процитировано

122
Dissociating language and thought in large language models DOI
Kyle Mahowald, Anna A. Ivanova, Idan Blank

и другие.

Trends in Cognitive Sciences, Год журнала: 2024, Номер 28(6), С. 517 - 540

Опубликована: Март 19, 2024

Язык: Английский

Процитировано

116
Bias and Fairness in Large Language Models: A Survey DOI Creative Commons

Isabel O. Gallegos,

Ryan A. Rossi,

Joe Barrow

и другие.

Computational Linguistics, Год журнала: 2024, Номер 50(3), С. 1097 - 1179

Опубликована: Янв. 1, 2024

Abstract Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these can learn, perpetuate, amplify harmful biases. In article, we present a comprehensive survey bias evaluation mitigation techniques for LLMs. We first consolidate, formalize, expand notions fairness in natural defining distinct facets harm introducing several desiderata to operationalize then unify literature by proposing three intuitive taxonomies, two evaluation, namely, metrics datasets, one mitigation. Our taxonomy disambiguates relationship between organizes different levels at which they operate model: embeddings, probabilities, generated text. second datasets categorizes their structure as counterfactual inputs or prompts, identifies targeted harms groups; also release consolidation publicly available improved access. third classifies methods intervention during pre-processing, in-training, intra-processing, post-processing, granular subcategories elucidate research trends. Finally, identify open problems challenges future work. Synthesizing wide range recent research, aim provide clear guide existing empowers researchers practitioners better understand prevent propagation

Язык: Английский

Процитировано

101
A guide to artificial intelligence for cancer researchers DOI
Raquel Pérez-López, Narmin Ghaffari Laleh, Faisal Mahmood

и другие.

Nature reviews. Cancer, Год журнала: 2024, Номер 24(6), С. 427 - 441

Опубликована: Май 16, 2024

Язык: Английский

Процитировано

67
Using LLMs to bring evidence-based feedback into the classroom: AI-generated feedback increases secondary students’ text revision, motivation, and positive emotions DOI Creative Commons
Jennifer Meyer, Thorben Jansen,

Ronja Schiller

и другие.

Computers and Education Artificial Intelligence, Год журнала: 2023, Номер 6, С. 100199 - 100199

Опубликована: Дек. 29, 2023

Writing proficiency is an essential skill for upper secondary students that can be enhanced through effective feedback. Creating feedback on writing tasks, however, time-intensive and presents a challenge educators, often resulting in receiving insufficient or no The advent of text-generating large language models (LLMs) offers promising solution, namely, automated evidence-based generation. Yet, empirical evidence from randomized controlled studies about the effectiveness LLM-generated missing. To address this issue, current study compared to A sample N = 459 English as foreign wrote argumentative essay. Students experimental group were asked revise their text according was generated using LLM GPT-3.5-turbo. control revised essays without We assessed improvement revision essay scoring. results showed increased performance (d .19) task motivation 0.36). Moreover, it positive emotions 0.34) revising findings highlight LLMs allows create timely positively relate students' cognitive affective-motivational outcomes. Future perspectives implications research practice intelligent tutoring systems are discussed.

Язык: Английский

Процитировано

62
Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI DOI Creative Commons
Mahyar Abbasian, Elahe Khatibi, Iman Azimi

и другие.

npj Digital Medicine, Год журнала: 2024, Номер 7(1)

Опубликована: Март 29, 2024

Язык: Английский

Процитировано

57