NAACL2025 Tutorial: Adaptation of Large Language Models

• URL: http://arxiv.org/abs/2504.03931v2
• Date: Mon, 21 Apr 2025 04:07:33 GMT
• Title: NAACL2025 Tutorial: Adaptation of Large Language Models
• Authors: Zixuan Ke, Yifei Ming, Shafiq Joty,
• Abstract summary: This tutorial on adaptation of LLMs is designed to address the growing demand for models that go beyond the static capabilities of generic LLMs.<n>We categorize adaptation techniques into two main families. The first is parametric knowledge adaptation, which focuses on updating the parametric knowledge within LLMs.<n>The second kind of adaptation is semi-parametric knowledge adaptation, where the goal is to update LLM parameters to better leverage external knowledge or tools.
• Score: 39.59753447841243
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This tutorial on adaptation of LLMs is designed to address the growing demand for models that go beyond the static capabilities of generic LLMs by providing an overview of dynamic, domain-specific, and task-adaptive LLM adaptation techniques. While general LLMs have demonstrated strong generalization across a variety of tasks, they often struggle to perform well in specialized domains such as finance, healthcare, and code generation for underrepresented languages. Additionally, their static nature limits their ability to evolve with the changing world, and they are often extremely large in size, making them impractical and costly to deploy at scale. As a result, the adaptation of LLMs has drawn much attention since the birth of LLMs and is of core importance, both for industry, which focuses on serving its targeted users, and academia, which can greatly benefit from small but powerful LLMs. To address this gap, this tutorial aims to provide an overview of the LLM adaptation techniques. We start with an introduction to LLM adaptation, from both the data perspective and the model perspective. We then emphasize how the evaluation metrics and benchmarks are different from other techniques. After establishing the problems, we explore various adaptation techniques. We categorize adaptation techniques into two main families. The first is parametric knowledge adaptation, which focuses on updating the parametric knowledge within LLMs. Additionally, we will discuss real-time adaptation techniques, including model editing, which allows LLMs to be updated dynamically in production environments. The second kind of adaptation is semi-parametric knowledge adaptation, where the goal is to update LLM parameters to better leverage external knowledge or tools through techniques like retrieval-augmented generation (RAG) and agent-based systems.

Related papers

• Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks [0.0]
  Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP) This study evaluates the continual fine-tuning of various open-source LLMs on key NLU tasks. Our results indicate that models such as Phi-3.5-mini exhibit minimal forgetting while maintaining strong learning capabilities.
  arXiv  Detail & Related papers  (2025-04-01T23:06:55Z)
• Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model [63.14883657299359]
  Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. tuning MLLMs for downstream tasks encounters two key challenges: Task-Expert, where distribution shifts between pre-training and target datasets constrain target performance, and OpenWorld Stabilization, where catastrophic forgetting erases the model general knowledge.
  arXiv  Detail & Related papers  (2025-03-06T15:29:13Z)
• LLM Post-Training: A Deep Dive into Reasoning Large Language Models [131.10969986056]
  Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications.<n>Post-training methods enable LLMs to refine their knowledge, improve reasoning, enhance factual accuracy, and align more effectively with user intents and ethical considerations.
  arXiv  Detail & Related papers  (2025-02-28T18:59:54Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression. LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model. Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing [21.143790515287392]
  Large language models (LLMs) have achieved remarkable performance on various natural language tasks. They are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing (KE) to update specific knowledge in LLMs without changing unrelated others or compromising their pre-trained capabilities.
  arXiv  Detail & Related papers  (2025-02-02T00:10:51Z)
• Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices [32.61693246340064]
  We study how a resource-constrained computing environment would affect the design choices for a personalized LLM. We consider the tradeoffs among a number of key design factors and their intertwined impacts on learning efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-06-06T06:41:53Z)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)<n>We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• When Life gives you LLMs, make LLM-ADE: Large Language Models with Adaptive Data Engineering [0.0]
  LLM-ADE is a methodology for continued pre-training of large language models. It addresses the challenges of catastrophic forgetting and double descent. It enhances model adaptability to new data while preserving previously acquired knowledge.
  arXiv  Detail & Related papers  (2024-04-19T17:43:26Z)
• Continual Learning for Large Language Models: A Survey [95.79977915131145]
  Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale. This paper surveys recent works on continual learning for LLMs.
  arXiv  Detail & Related papers  (2024-02-02T12:34:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.