Bartłomiej Koptyra

ORCID: 0009-0005-9938-305X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Sentiment Analysis and Opinion Mining
  • Natural Language Processing Techniques
  • Artificial Intelligence in Healthcare and Education
  • Evolutionary Algorithms and Applications
  • Reinforcement Learning in Robotics
  • Computational and Text Analysis Methods
  • Domain Adaptation and Few-Shot Learning
  • Explainable Artificial Intelligence (XAI)
  • COVID-19 diagnosis using AI
  • Stock Market Forecasting Methods
  • Advanced Neural Network Applications
  • Machine Learning in Healthcare

Wrocław University of Science and Technology
2023

AGH University of Krakow
2023

OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and revolutionized approach in artificial intelligence to human-model interaction. The first contact with chatbot reveals its ability provide detailed precise answers various areas. Several publications on ChatGPT evaluation test effectiveness well-known natural language processing (NLP) tasks. However, existing studies are mostly non-automated tested a very limited scale. In this work, we examined ChatGPT's...

10.1016/j.inffus.2023.101861 article EN cc-by Information Fusion 2023-06-03

Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu. Findings of the Association for...

10.18653/v1/2023.findings-emnlp.936 article EN cc-by 2023-01-01

OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and revolutionized approach in artificial intelligence to human-model interaction. The first contact with chatbot reveals its ability provide detailed precise answers various areas. There are several publications on ChatGPT evaluation, testing effectiveness well-known natural language processing (NLP) tasks. However, existing studies mostly non-automated tested a very limited scale. In this work, we examined ChatGPT's...

10.2139/ssrn.4372889 article EN 2023-01-01

OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and revolutionized approach in artificial intelligence to human-model interaction. Several publications on ChatGPT evaluation test its effectiveness well-known natural language processing (NLP) tasks. However, existing studies are mostly non-automated tested a very limited scale. In this work, we examined ChatGPT's capabilities 25 diverse analytical NLP tasks, most of them subjective even humans, such as sentiment...

10.48550/arxiv.2302.10724 preprint EN cc-by arXiv (Cornell University) 2023-01-01

Large language models (LLMs) have significantly advanced Natural Language Processing (NLP) tasks in recent years. However, their universal nature poses limitations scenarios requiring personalized responses, such as recommendation systems and chatbots. This paper investigates methods to personalize LLMs, comparing fine-tuning zero-shot reasoning approaches on subjective tasks. Results demonstrate that improves model compared non-personalized models. Experiments datasets for emotion...

10.48550/arxiv.2402.09269 preprint EN arXiv (Cornell University) 2024-02-14

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in requirements struggle to match the same performance as due limitations parallelization scalability. We propose a novel model architecture, Receptance Weighted Key Value (RWKV), combines efficient parallelizable training of transformers...

10.48550/arxiv.2305.13048 preprint EN cc-by arXiv (Cornell University) 2023-01-01

We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-valued states a dynamic recurrence mechanism that improve expressivity while maintaining inference efficiency characteristics of RNNs. introduce new multilingual corpus with 1.12 trillion tokens fast tokenizer based on greedy matching for enhanced multilinguality. trained four models, ranging from 0.46 to 7.5 billion...

10.48550/arxiv.2404.05892 preprint EN arXiv (Cornell University) 2024-04-08

10.1109/icdmw65004.2024.00071 article 2022 IEEE International Conference on Data Mining Workshops (ICDMW) 2024-12-09

10.1109/icdmw65004.2024.00065 article EN 2022 IEEE International Conference on Data Mining Workshops (ICDMW) 2024-12-09
Coming Soon ...