How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

• URL: http://arxiv.org/abs/2502.14502v1
• Date: Thu, 20 Feb 2025 12:31:03 GMT
• Title: How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
• Authors: Sergey Pletenev, Maria Marina, Daniil Moskovskiy, Vasily Konovalov, Pavel Braslavski, Alexander Panchenko, Mikhail Salnikov,
• Abstract summary: Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of Large Language Models. We investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge.
• Score: 55.33467849079774
• License:
• Abstract: The performance of Large Language Models (LLMs) on many tasks is greatly limited by the knowledge learned during pre-training and stored in the model's parameters. Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of LLMs. In this study, we investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge. We fine-tuned Llama-3.1-8B-instruct using LoRA with varying amounts of new knowledge. Our experiments have shown that the best results are obtained when the training data contains a mixture of known and new facts. However, this approach is still potentially harmful because the model's performance on external question-answering benchmarks declines after such fine-tuning. When the training data is biased towards certain entities, the model tends to regress to few overrepresented answers. In addition, we found that the model becomes more confident and refuses to provide an answer in only few cases. These findings highlight the potential pitfalls of LoRA-based LLM updates and underscore the importance of training data composition and tuning parameters to balance new knowledge integration and general model capabilities.

Related papers

• Post-training an LLM for RAG? Train on Self-Generated Demonstrations [18.8726880078299]
  Large language models (LLMs) often struggle with knowledge intensive NLP tasks. Retrieval augmented generation (RAG) allows the model to leverage in-context information. We propose a recipe for training RAG-enabled LLMs using self-generated demonstrations.
  arXiv  Detail & Related papers  (2025-02-14T23:00:49Z)
• The Scaling Law for LoRA Base on Mutual Information Upper Bound [16.527968425791393]
  In fine-tuning, the law among model performance, model parameters, and data complexity has been a focal issue in the field. We propose an internal metric based on the Mutual Information Upper Bound (MIUB) theory to investigate the scaling law of large-model LoRA fine-tuning. The proposed MIUB metric aligns more accurately and stably with the scaling law of LoRA fine-tuning compared to cross-entropy and perplexity.
  arXiv  Detail & Related papers  (2025-01-06T17:19:19Z)
• DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning [23.878495627964146]
  Continual learning aims to equip models with the ability to retain previously learned knowledge like a human. Existing methods usually overlook the issue of information leakage caused by the fact that the experiment data have been used in pre-trained models. In this paper, we propose a new LoRA-based rehearsal-free method named DESIRE.
  arXiv  Detail & Related papers  (2024-11-28T13:54:01Z)
• Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs [50.29035873837]
  Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. Long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models' memorization. We propose a reinforcement learning-based dynamic uncertainty ranking method for ICL that accounts for the varying impact of each retrieved sample on LLM predictions.
  arXiv  Detail & Related papers  (2024-10-31T03:42:17Z)
• Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models [38.197552424549514]
  Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models. LoRAs present opportunities for applying machine learning techniques that take these low-rank weights themselves as inputs. In this paper, we investigate the potential of Learning on LoRAs (LoL), a paradigm where LoRA weights serve as input to machine learning models.
  arXiv  Detail & Related papers  (2024-10-05T15:52:47Z)
• Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation [50.837277466987345]
  We focus on the field of large language models (LLMs) for recommendation. We propose RecLoRA, which incorporates a Personalized LoRA module that maintains independent LoRAs for different users. We also design a Few2Many Learning Strategy, using a conventional recommendation model as a lens to magnify small training spaces to full spaces.
  arXiv  Detail & Related papers  (2024-08-07T04:20:28Z)
• Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs [60.40396361115776]
  This paper introduces a novel collaborative approach, namely SlimPLM, that detects missing knowledge in large language models (LLMs) with a slim proxy model. We employ a proxy model which has far fewer parameters, and take its answers as answers. Heuristic answers are then utilized to predict the knowledge required to answer the user question, as well as the known and unknown knowledge within the LLM.
  arXiv  Detail & Related papers  (2024-02-19T11:11:08Z)
• Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models [53.52344131257681]
  We propose a new paradigm for fine-tuning called F-Learning, which employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge. Experimental results on two publicly available datasets demonstrate that our proposed F-Learning can obviously improve the knowledge updating performance of both full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2023-11-14T09:12:40Z)
• An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning [70.48605869773814]
  Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information. This study empirically evaluates the forgetting phenomenon in large language models during continual instruction tuning.
  arXiv  Detail & Related papers  (2023-08-17T02:53:23Z)

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.