Learn Before
Fine-Tuning LLMs with External Memory
One example of architectural adaptation via fine-tuning involves models augmented with external memory, such as in Retrieval-Augmented Generation (RAG). In this setup, the pre-trained LLM's parameters are often kept fixed, and fine-tuning is used to train the model to effectively collaborate with the external memory component and better utilize the retrieved information.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Ch.2 Generative Models - Foundations of Large Language Models
Related
Fine-Tuning LLMs with External Memory
Fine-Tuning with Swapped Attention Mechanisms
Adapting a Pre-Trained Model for a New Task
A research team starts with a large language model that was pre-trained using a standard, computationally intensive attention mechanism. To make the model more efficient for processing very long documents, they replace this original mechanism with a novel, more memory-efficient one. They then continue training this architecturally modified model on a specialized dataset of long legal texts. What does this successful adaptation primarily demonstrate about the fine-tuning process?
Strategy for Architectural Model Adaptation
Fine-Tuning for Sparse Attention Adaptation
Learn After
Fine-Tuning LLMs to Enhance RAG Performance
A financial services company wants to deploy a chatbot to help its advisors answer client questions. The chatbot must use the company's proprietary, 500-page market analysis report, which is updated weekly. The company uses a powerful, general-purpose pre-trained language model but finds it gives generic advice, not specific insights from the report. Given the need for up-to-date, report-specific answers and a desire to minimize computational costs, which approach is most suitable?
Diagnosing a Faulty Knowledge-Augmented System
Distinguishing Roles in a Memory-Augmented System