Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913652822507520 |
|---|---|
| author | Erak, Omar Alabbasi, Nouf Alhussein, Omar Lotfi, Ismail Hussein, Amr Muhaidat, Sami Debbah, Merouane |
| author_facet | Erak, Omar Alabbasi, Nouf Alhussein, Omar Lotfi, Ismail Hussein, Amr Muhaidat, Sami Debbah, Merouane |
| contents | Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system based on the Phi-2 small language model (SLM) to serve as an oracle for communication networks. Our developed system leverages forward-looking semantic chunking to adaptively determine parsing breakpoints based on embedding similarity, enabling effective processing of diverse document formats. To handle the challenge of multiple similar contexts in technical standards, we employ a re-ranking algorithm to prioritize the most relevant retrieved chunks. Recognizing the limitations of Phi-2's small context window, we implement a recent technique, namely SelfExtend, to expand the context window during inference, which not only boosts the performance but also can accommodate a wider range of user queries and design requirements from customers to specialized technicians. For fine-tuning, we utilize the low-rank adaptation (LoRA) technique to enhance computational efficiency during training and enable effective fine-tuning on small datasets. Our comprehensive experiments demonstrate substantial improvements over existing question-answering approaches in the telecom domain, achieving performance that exceeds larger language models such as GPT-4 (which is about 880 times larger in size). This work presents a novel approach to leveraging SLMs for communication networks, offering a balance of efficiency and performance. This work can serve as a foundation towards agentic language models for networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11775 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards Erak, Omar Alabbasi, Nouf Alhussein, Omar Lotfi, Ismail Hussein, Amr Muhaidat, Sami Debbah, Merouane Computation and Language Networking and Internet Architecture Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system based on the Phi-2 small language model (SLM) to serve as an oracle for communication networks. Our developed system leverages forward-looking semantic chunking to adaptively determine parsing breakpoints based on embedding similarity, enabling effective processing of diverse document formats. To handle the challenge of multiple similar contexts in technical standards, we employ a re-ranking algorithm to prioritize the most relevant retrieved chunks. Recognizing the limitations of Phi-2's small context window, we implement a recent technique, namely SelfExtend, to expand the context window during inference, which not only boosts the performance but also can accommodate a wider range of user queries and design requirements from customers to specialized technicians. For fine-tuning, we utilize the low-rank adaptation (LoRA) technique to enhance computational efficiency during training and enable effective fine-tuning on small datasets. Our comprehensive experiments demonstrate substantial improvements over existing question-answering approaches in the telecom domain, achieving performance that exceeds larger language models such as GPT-4 (which is about 880 times larger in size). This work presents a novel approach to leveraging SLMs for communication networks, offering a balance of efficiency and performance. This work can serve as a foundation towards agentic language models for networks. |
| title | Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards |
| topic | Computation and Language Networking and Internet Architecture |
| url | https://arxiv.org/abs/2408.11775 |