Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching

• URL: http://arxiv.org/abs/2406.06326v4
• Date: Sat, 15 Feb 2025 03:22:07 GMT
• Title: Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
• Authors: Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Yipeng Zhang, Haitao Mi, Helen Meng,
• Abstract summary: Large language models (LLMs) often struggle to provide up-to-date information. Existing approaches typically involve continued pre-training on new documents. Motivated by the success of the Feynman Technique in efficient human learning, we introduce Self-Tuning.
• Score: 67.11497198002165
• License:
• Abstract: Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training on new documents. However, they frequently face difficulties in extracting stored knowledge. Motivated by the remarkable success of the Feynman Technique in efficient human learning, we introduce Self-Tuning, a learning framework aimed at improving an LLM's ability to effectively acquire new knowledge from unseen raw documents through self-teaching. Specifically, we develop a Self-Teaching strategy that augments the documents with a set of knowledge-intensive tasks created in a self-supervised manner, focusing on three crucial aspects: memorization, comprehension, and self-reflection. Additionally, we introduce three Wiki-Newpages-2023-QA datasets to facilitate an in-depth analysis of an LLM's knowledge acquisition ability concerning memorization, extraction, and reasoning. Extensive experimental results on various models, e.g., Llama2-7B reveal that Self-Tuning consistently exhibits superior performance across all knowledge acquisition tasks and excels in preserving previous knowledge.

Related papers

• How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training [92.88889953768455]
  Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge. We identify computational subgraphs that facilitate knowledge storage and processing.
  arXiv  Detail & Related papers  (2025-02-16T16:55:43Z)
• Refine Knowledge of Large Language Models via Adaptive Contrastive Learning [54.61213933999464]
  A mainstream category of methods is to reduce hallucinations by optimizing the knowledge representation of Large Language Models. We believe that the process of models refining knowledge can greatly benefit from the way humans learn. In our work, by imitating the human learning process, we design an Adaptive Contrastive Learning strategy.
  arXiv  Detail & Related papers  (2025-02-11T02:19:13Z)
• WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge [17.74988145184004]
  Large language models (LLMs) have emerged as powerful tools in natural language processing (NLP) This paper presents a novel LLM for education named WisdomBot, which combines the power of LLMs with educational theories. We introduce two key enhancements during inference, i.e., local knowledge base retrieval augmentation and search engine retrieval augmentation during inference.
  arXiv  Detail & Related papers  (2025-01-22T13:36:46Z)
• KaLM: Knowledge-aligned Autoregressive Language Modeling via Dual-view Knowledge Graph Contrastive Learning [74.21524111840652]
  This paper proposes textbfKaLM, a textitKnowledge-aligned Language Modeling approach. It fine-tunes autoregressive large language models to align with KG knowledge via the joint objective of explicit knowledge alignment and implicit knowledge alignment. Notably, our method achieves a significant performance boost in evaluations of knowledge-driven tasks.
  arXiv  Detail & Related papers  (2024-12-06T11:08:24Z)
• KBAlign: Efficient Self Adaptation on Specific Knowledge Bases [73.34893326181046]
  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)
• "Flipped" University: LLM-Assisted Lifelong Learning Environment [1.0742675209112622]
  This paper introduces a conceptual framework for a self-constructed lifelong learning environment supported by Large Language Models (LLMs) The proposed framework emphasizes the transformation from institutionalized education to personalized, self-driven learning. The paper envisions the evolution of educational institutions into "flipped" universities, focusing on supporting global knowledge consistency.
  arXiv  Detail & Related papers  (2024-09-02T13:27:36Z)
• TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models [31.209774088374374]
  This paper introduces TRELM, a Robust and Efficient Pre-training framework for Knowledge-Enhanced Language Models. We employ a robust approach to inject knowledge triples and employ a knowledge-augmented memory bank to capture valuable information. We show that TRELM reduces pre-training time by at least 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.
  arXiv  Detail & Related papers  (2024-03-17T13:04:35Z)
• 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)
• Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning [18.61040106667249]
  In AI, generalization refers to a model's ability to perform well on out-of-distribution data related to a given task, beyond the data it was trained on. Continual learning methods often include mechanisms to mitigate catastrophic forgetting, ensuring that knowledge from earlier tasks is retained. We introduce a simple and effective technique known as Shape-Texture Consistency Regularization (STCR), which caters to continual learning.
  arXiv  Detail & Related papers  (2022-11-21T04:36:24Z)

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.