Research output per year
Research output per year
Project Details
Description
Actively applied for TDF to secure fund in 2023 SEM 2 for further advancement in this research direction.
Key findings
1.This research explores a new idea where two large-language models are used to create a conversation-style teaching course while supervising each other's content to avoid false information.
2.Large-language models (LLMs) have become increasingly popular and are being used by many companies and individuals for various tasks. However, the complexity of LLMs makes their output highly unpredictable, resulting in misinformation.
3.This research aims to address this issue by encouraging AI models to correct each other, thereby improving accuracy and reliability for tasks that require fact checking.
| Project Category | SELF FUNDING |
|---|---|
| Acronym | SF |
| Status | Active |
| Effective start/end date | 1/01/23 → … |
Keywords
- Large Language Model
- Language Training
- Cloud
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.
Research output
- 1 Conference Proceeding
-
Evaluation and Language Training of Multinational Enterprises Employees by Deep Learning in Cloud Manufacturing Resources: https://link.springer.com/chapter/10.1007/978-981-19-7455-7_28
Karn, A. L., 1 May 2023, 10th International Conference on Innovations in Computer Science & Engineering (ICICSE - 2022): Scopus indexed LNNS Springer. Springer, Vol. 565. p. 369 380 p.Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review