Fake News Detection with Large Language Models on the LIAR Dataset

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Май 24, 2024

The widespread dissemination of fake news poses a significant threat to the integrity information. Detecting with high accuracy is crucial for maintaining information in digital age. evaluation ChatGPT and Google Gemini models this task has revealed their substantial capabilities discerning veracity statements, highlighting potential mitigate spread misinformation. Using LIAR benchmark dataset, study demonstrated performance metrics across accuracy, precision, recall, F1 score, AUC-ROC, emphasizing effectiveness these real-world applications. comparative analysis error examination provided insights into strengths limitations each model, offering valuable guidance future enhancements. Practical implications include integration fact-checking systems improve content verification processes, supporting media organizations social platforms efforts combat findings prove importance ongoing research development refine optimize LLMs, ensuring continued relevance efficacy addressing challenges posed by news.

Язык: Английский

---

Exploring the Association Between Textual Parameters and Psychological and Cognitive Factors

Psychology Research and Behavior Management, Год журнала: 2024, Номер Volume 17, С. 1139 - 1150

Опубликована: Март 1, 2024

Textual data analysis has become a popular method for examining complex human behavior in various fields, including psychology, psychiatry, sociology, computer science, mining, forensic sciences, and communication studies. However, identifying the most relevant textual parameters analyzing is still challenge.

Язык: Английский

---

Virtual Teams: A Smart Literature Review of Four Decades of Research

Human Behavior and Emerging Technologies, Год журнала: 2024, Номер 2024, С. 1 - 20

Опубликована: Фев. 22, 2024

The increasing utilization of virtual teams—driven by advancements in information and communication technology the forces globalization—has spurred significant growth both theoretical empirical research. Based on smart literature review framework, this study harnesses artificial intelligence techniques, specifically natural language processing topic modeling, to extensively analyze trends team research spanning last four decades. Analyses a dataset comprising 2,184 articles from Scopus-indexed journals discern 16 distinct topics, encompassing critical areas such as communication, leadership, trust. trajectory topics field has witnessed diversification over time. Key subjects learning, trust, leadership have consistently maintained their presence among ten most frequently explored topics. In contrast, emerging agile development patient care recently become some prominent themes. Employing state-of-the-art modeling technique, BERTopic, furnishes comprehensive dynamic panorama evolving landscape within

Язык: Английский

---

Fraud detection at eBay

Emerging Markets Review, Год журнала: 2025, Номер unknown, С. 101277 - 101277

Опубликована: Март 1, 2025

---

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

Software, Год журнала: 2024, Номер 3(1), С. 62 - 80

Опубликована: Фев. 29, 2024

This paper presents a pioneering methodology for refining product recommender systems, introducing synergistic integration of unsupervised models—K-means clustering, content-based filtering (CBF), and hierarchical clustering—with the cutting-edge GPT-4 large language model (LLM). Its innovation lies in utilizing evaluation, harnessing its advanced natural understanding capabilities to enhance precision relevance recommendations. A flask-based API simplifies implementation e-commerce owners, allowing seamless training evaluation models using CSV-formatted data. The unique aspect this approach ability empower with sophisticated system algorithms, while GPT significantly contributes semantic context features, resulting more personalized effective recommendation system. experimental results underscore superiority integrated framework, marking significant advancement field systems providing businesses an efficient scalable solution optimize their

Язык: Английский

---

Next-Generation Spam Filtering: Comparative Fine-Tuning of LLMs, NLPs, and CNN Models for Email Spam Classification

Electronics, Год журнала: 2024, Номер 13(11), С. 2034 - 2034

Опубликована: Май 23, 2024

Spam emails and phishing attacks continue to pose significant challenges email users worldwide, necessitating advanced techniques for their efficient detection classification. In this paper, we address the persistent of spam by introducing a cutting-edge approach filtering. Our methodology revolves around harnessing capabilities language models, particularly state-of-the-art GPT-4 Large Language Model (LLM), along with BERT RoBERTa Natural Processing (NLP) models. Through meticulous fine-tuning tailored classification tasks, aim surpass limitations traditional systems, such as Convolutional Neural Networks (CNNs). an extensive literature review, experimentation, evaluation, demonstrate effectiveness our in accurately identifying while minimizing false positives. showcases potential LLMs specialized tasks like classification, offering enhanced protection against evolving attacks. This research contributes advancement filtering lays groundwork robust security systems face increasingly sophisticated threats.

Язык: Английский

---

Large language model to multimodal large language model: A journey to shape the biological macromolecules to biological sciences and medicine

Molecular Therapy — Nucleic Acids, Год журнала: 2024, Номер 35(3), С. 102255 - 102255

Опубликована: Июнь 15, 2024

After ChatGPT was released, large language models (LLMs) became more popular. Academicians use or LLM for different purposes, and the of is increasing from medical science to diversified areas. Recently, multimodal (MLLM) has also become Therefore, we comprehensively illustrate MLLM a complete understanding. We aim simple extended reviews LLMs MLLMs broad category readers, such as researchers, students in fields, other academicians. The review article illustrates models, their working principles, applications fields. First, demonstrate technical concept LLMs, principle, Black Box, evolution LLMs. To explain discuss tokenization process, token representation, relationships. extensively application biological macromolecules, science, MLLMs. Finally, limitations, challenges, future prospects acts booster dose clinicians, primer molecular biologists, catalyst scientists, benefits

Язык: Английский

---

Customer Sentiments in Product Reviews: A Comparative Study with GooglePaLM

Analytics, Год журнала: 2024, Номер 3(2), С. 241 - 254

Опубликована: Июнь 18, 2024

In this work, we evaluated the efficacy of Google’s Pathways Language Model (GooglePaLM) in analyzing sentiments expressed product reviews. Although conventional Natural Processing (NLP) techniques such as rule-based Valence Aware Dictionary for Sentiment Reasoning (VADER) and long sequence Bidirectional Encoder Representations from Transformers (BERT) model are effective, they frequently encounter difficulties when dealing with intricate linguistic features like sarcasm contextual nuances commonly found customer feedback. We performed a sentiment analysis on Amazon’s fashion review datasets using VADER, BERT, GooglePaLM models, respectively, compared results based evaluation metrics precision, recall, accuracy correct positive prediction, negative prediction. used default values VADER BERT models slightly finetuned Temperature 0.0 an N-value 1. observed that better prediction 0.91 0.93, followed by VADER. concluded large language surpass traditional systems natural processing tasks.

Язык: Английский

---

A discrete convolutional network for entity relation extraction

Neural Networks, Год журнала: 2025, Номер 184, С. 107117 - 107117

Опубликована: Янв. 6, 2025

Язык: Английский

---

Fine‐tuning XLNet for Amazon review sentiment analysis: A comparative evaluation of transformer models

ETRI Journal, Год журнала: 2025, Номер unknown

Опубликована: Фев. 12, 2025

Abstract Transfer learning in large language models adapts pretrained to new tasks by leveraging their existing linguistic knowledge for domain‐specific applications. A fine‐tuned XLNet, base‐cased model is proposed classifying Amazon product reviews. Two datasets are used evaluate the approach: earphone and personal computer Model performance benchmarked against transformer including ELECTRA, BERT, RoBERTa, ALBERT, DistilBERT. In addition, hybrid such as CNN‐LSTM CNN‐BiLSTM considered conjunction with single CNN, BiGRU, BiLSTM. The XLNet achieved accuracies of 95.2% reviews 95% accuracy ELECTRA slightly lower than that XLNet. exact match ratio values on AE AP 0.95 0.94, respectively. exceptional F1 scores, outperforming all other models. was different rates, optimizers (such Nadam Adam), batch sizes (4, 8, 16). This analysis underscores effectiveness approach sentiment tasks.

Язык: Английский

---