A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios

• URL: http://arxiv.org/abs/2511.00130v2
• Date: Tue, 04 Nov 2025 17:53:35 GMT
• Title: A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
• Authors: Bernd Bohnet, Rumen Dangovski, Kevin Swersky, Sherry Moore, Arslan Chaudhry, Kathleen Kenealy, Noah Fiedel,
• Abstract summary: Full fine-tuning is a powerful adaptation method but can lead to a degradation of general reasoning abilities.<n>Low-Rank Adaptation (LoRA) provides the most effective balance, successfully instilling new skills with minimal impact on the base model's general knowledge.<n>We highlight the critical distinction between skill acquisition and knowledge integration, clarify the trade-offs between task-specific performance and the preservation of general capabilities.
• Score: 11.964783773016363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The remarkable capabilities of Large Language Models (LLMs) often need to be tailored for specific applications, requiring the integration of new knowledge or the acquisition of new skills. While full fine-tuning is a powerful adaptation method, it is computationally expensive and can lead to a degradation of general reasoning abilities, a phenomenon known as catastrophic forgetting. A range of alternative techniques exists, each with its own trade-offs. In-Context Learning (ICL) is fast but limited by context length, while Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) offer a middle ground by minimizing parameter changes. However, the challenge of catastrophic forgetting persists, raising questions about the best adaptation strategy for a given task. This paper presents a comparative analysis of Supervised Finetuning (SFT), LoRA, and ICL in data-scarce scenarios. We find that LoRA provides the most effective balance, successfully instilling new skills with minimal impact on the base model's general knowledge. In contrast, while SFT excels at skill acquisition, it is highly susceptible to catastrophic forgetting. ICL is effective for incorporating factual knowledge but struggles with complex skills. Our findings offer a practical framework for selecting an LLM adaptation strategy. We highlight the critical distinction between skill acquisition and knowledge integration, clarify the trade-offs between task-specific performance and the preservation of general capabilities.

Related papers

• SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs [53.77646961962239]
  Supervised Fine-Tuning (SFT) is a common approach to adapt Large Language Models (LLMs) to specialized tasks.<n>We show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation.
  arXiv  Detail & Related papers  (2025-09-25T05:28:22Z)
• KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance [83.99974309930072]
  Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs)
  arXiv  Detail & Related papers  (2025-05-21T12:55:28Z)
• CoLA: Collaborative Low-Rank Adaptation [3.421904493396495]
  Fine-tuning a pre-trained model for specific tasks achieves strong performance; however, it is computationally expensive and inefficient.<n>LoRA, in particular, has proven effective, but its application to multi-task scenarios is limited by interference between tasks.<n>We propose CoLA, a more flexible LoRA architecture and three collaborative strategies to enhance performance by better utilizing the quantitative relationships between $A$ and $B$.
  arXiv  Detail & Related papers  (2025-05-21T12:46:42Z)
• How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? [55.33467849079774]
  Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of Large Language Models.<n>We investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-02-20T12:31:03Z)
• Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving [55.895917967408586]
  Existing approaches to mathematical reasoning with large language models rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation.<n>We propose TATA (Teaching LLMs According to Their Aptitude), an adaptive framework that enables LLMs to personalize their reasoning strategy spontaneously.
  arXiv  Detail & Related papers  (2025-02-17T16:56:23Z)
• Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context [24.905102026459428]
  Transformers have demonstrated remarkable in-context learning capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates.<n>It remains unclear to what extent the transformers optimally learn in-context compared to principled learning algorithms.
  arXiv  Detail & Related papers  (2025-02-07T00:26:45Z)
• Unified Parameter-Efficient Unlearning for LLMs [25.195126838721492]
  Large Language Models (LLMs) have revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks.<n>This raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information.<n>We introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise adjustments using influence functions.
  arXiv  Detail & Related papers  (2024-11-30T07:21:02Z)
• Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
  Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
  arXiv  Detail & Related papers  (2024-10-25T17:07:13Z)
• KIF: Knowledge Identification and Fusion for Language Model Continual Learning [41.28933724210434]
  We introduce a novel framework for language models, named Knowledge Identification and Fusion (KIF)<n>KIF segregates the model into'skill units' based on parameter dependencies, allowing for more precise control.<n>It employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task.<n>As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks.
  arXiv  Detail & Related papers  (2024-08-09T17:44:45Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• HFT: Half Fine-Tuning for Large Language Models [42.60438623804577]
  Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities. In this paper, we find that by regularly resetting partial parameters, LLMs can restore some of the original knowledge. We introduce Half Fine-Tuning (HFT) for LLMs, as a substitute for full fine-tuning (FFT), to mitigate the forgetting issues.
  arXiv  Detail & Related papers  (2024-04-29T07:07:58Z)

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.