Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning

• URL: http://arxiv.org/abs/2404.00213v2
• Date: Tue, 2 Apr 2024 20:09:45 GMT
• Title: Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning
• Authors: Nick Mecklenburg, Yiyou Lin, Xiaoxiao Li, Daniel Holstein, Leonardo Nunes, Sara Malvar, Bruno Silva, Ranveer Chandra, Vijay Aski, Pavan Kumar Reddy Yannam, Tolga Aktas, Todd Hendry,
• Abstract summary: This paper investigates the effectiveness ofSupervised Fine-Tuning (SFT) as a method for knowledge injection in Large Language Models (LLMs) We compare different dataset generation strategies -- token-based and fact-based scaling -- to create training data that helps the model learn new information. Our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge.
• Score: 13.371405067535814
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In recent years, Large Language Models (LLMs) have shown remarkable performance in generating human-like text, proving to be a valuable asset across various applications. However, adapting these models to incorporate new, out-of-domain knowledge remains a challenge, particularly for facts and events that occur after the model's knowledge cutoff date. This paper investigates the effectiveness of Supervised Fine-Tuning (SFT) as a method for knowledge injection in LLMs, specifically focusing on the domain of recent sporting events. We compare different dataset generation strategies -- token-based and fact-based scaling -- to create training data that helps the model learn new information. Our experiments on GPT-4 demonstrate that while token-based scaling can lead to improvements in Q&A accuracy, it may not provide uniform coverage of new knowledge. Fact-based scaling, on the other hand, offers a more systematic approach to ensure even coverage across all facts. We present a novel dataset generation process that leads to more effective knowledge ingestion through SFT, and our results show considerable performance improvements in Q&A tasks related to out-of-domain knowledge. This study contributes to the understanding of domain adaptation for LLMs and highlights the potential of SFT in enhancing the factuality of LLM responses in specific knowledge domains.

Related papers

• KBAlign: Efficient Self Adaptation on Specific Knowledge Bases [75.78948575957081]
  Large language models (LLMs) usually rely on retrieval-augmented generation to exploit knowledge materials in an instant manner. We propose KBAlign, an approach designed for efficient adaptation to downstream tasks involving knowledge bases. Our method utilizes iterative training with self-annotated data such as Q&A pairs and revision suggestions, enabling the model to grasp the knowledge content efficiently.
  arXiv  Detail & Related papers  (2024-11-22T08:21:03Z)
• Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models [1.753683416932648]
  Large language models (LLMs) are proficient in capturing factual knowledge across various domains. In this work, we propose a novel synthetic knowledge ingestion method called Ski. We then integrate Ski and its variations with three knowledge injection techniques to inject and refine knowledge in language models.
  arXiv  Detail & Related papers  (2024-10-12T19:38:09Z)
• Investigating Continual Pretraining in Large Language Models: Insights and Implications [9.591223887442704]
  This paper studies the evolving domain of Continual Learning in large language models (LLMs) Our primary emphasis is on continual domain-adaptive pretraining, a process designed to equip LLMs with the ability to integrate new information from various domains. We examine the impact of model size on learning efficacy and forgetting, as well as how the progression and similarity of emerging domains affect the knowledge transfer within these models.
  arXiv  Detail & Related papers  (2024-02-27T10:47:24Z)
• LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition [67.96794382040547]
  $LLM-DA$ is a novel data augmentation technique based on large language models (LLMs) for the few-shot NER task. Our approach involves employing 14 contextual rewriting strategies, designing entity replacements of the same type, and incorporating noise injection to enhance robustness.
  arXiv  Detail & Related papers  (2024-02-22T14:19:56Z)
• A Closer Look at the Limitations of Instruction Tuning [52.587607091917214]
  We show that Instruction Tuning (IT) fails to enhance knowledge or skills in large language models (LLMs) We also show that popular methods to improve IT do not lead to performance improvements over a simple LoRA fine-tuned model. Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets.
  arXiv  Detail & Related papers  (2024-02-03T04:45:25Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)
• 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)
• Knowledge Editing for Large Language Models: A Survey [51.01368551235289]
  One major drawback of large language models (LLMs) is their substantial computational cost for pre-training. Knowledge-based Model Editing (KME) has attracted increasing attention, which aims to precisely modify the LLMs to incorporate specific knowledge.
  arXiv  Detail & Related papers  (2023-10-24T22:18:13Z)

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.