paper-with-me

홈 › Papers

Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards

2024-08-21 · Omar Erak, Nouf Alabbasi, Omar Alhussein, Ismail Lotfi, Amr Hussein, Sami Muhaidat, Merouane Debbah

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.

📄 PDF Abstract BibTeX arXiv:2408.11775

Code (1)

Nouf-Alabbasi/oKUmura_AI_Telecom_challenge 공식 구현 pytorch

Tasks

ChunkingComputational EfficiencyLanguage ModellingQuestion AnsweringRAGRe-RankingRetrievalRetrieval-augmented GenerationSmall Language Model

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation

2026-04-14 · Gibson Nkhata, Uttamasha Anjally Oyshi, Quan Mai, Susan Gauch arxiv

Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often suffer from high retrieval costs and overlook that collaborative signal…

Collaborative Filtering

LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks

2025-07-07 · William Fleshman, Benjamin Van Durme arxiv

The proliferation of fine-tuned language model experts for specific tasks and domains signals the need for efficient selection and combination methods. We propose LoRA-Augmented Generation (LAG) for leveraging large libr…

LLM-Match: An Open-Sourced Patient Matching Model Based on Large Language Models and Retrieval-Augmented Generation

2025-03-17 · Xiaodi Li, Shaika Chowdhury, Chung Il Wi, Maria Vassilaki 외

Patient matching is the process of linking patients to appropriate clinical trials by accurately identifying and matching their medical records with trial eligibility criteria. We propose LLM-Match, a novel framework for…

RAGRetrieval-augmented Generation

Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models

2024-10-24 · Fengchen Liu, Jordan Jung, Wei Feinstein, Jeff DAmbrogia 외

This paper introduces a novel approach to enhancing closed-domain Question Answering (QA) systems, focusing on the specific needs of the Lawrence Berkeley National Laboratory (LBL) Science Information Technology (Science…

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Leveraging Lora Fine-Tuning and Knowledge Bases for Construction Identification

2026-01-19 · Liu Kaipeng, Wu Ling arxiv

This study investigates the automatic identification of the English ditransitive construction by integrating LoRA-based fine-tuning of a large language model with a Retrieval-Augmented Generation (RAG) framework.A binary…

Binary Classification