Foundation Models and Large Language Models in Next Generation Networks: Comparison, Opportunities and Challenges
Bibliographic record
Abstract
Next-generation networks (NGNs) face growing demands for more bandwidth, lower delay, and better intelligence. Foundation Models (FMs) and Large Language Models (LLMs) are powerful generative artificial intelligence models that could help meet these demands. However, there is confusion about their differences and how best to use them in NGNs. This research survey presents a detailed evaluation of FMs against LLMs to illustrate the distinct characteristics and benefits of both models. The work also examines NGN applications, which include network traffic analysis enhancement and network management automation, as well as security improvement through the use of these models. The research paper discusses vital enabling techniques that are needed to train and customize the current models. Research results show that NGNs experience improved intelligent operations through the use of FMs together with LLMs. The process of implementing FMs and LLMs, along with their training, encounters obstacles that include demanding data as well as high computational expenses and security issues. The study emphasizes that future NGNs require FMs and LLMs to succeed; yet, further studies are necessary to overcome existing obstacles and reach their complete capabilities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.006 | 0.013 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".