Knowledge Circuits in Pretrained Transformers

• URL: http://arxiv.org/abs/2405.17969v2
• Date: Wed, 16 Oct 2024 03:35:22 GMT
• Title: Knowledge Circuits in Pretrained Transformers
• Authors: Yunzhi Yao, Ningyu Zhang, Zekun Xi, Mengru Wang, Ziwen Xu, Shumin Deng, Huajun Chen,
• Abstract summary: The inner workings of how modern large language models store knowledge have long been a subject of intense interest and investigation among researchers. In this paper, we delve into the graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. We evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies.
• Score: 47.342682123081204
• License:
• Abstract: The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these models store knowledge have long been a subject of intense interest and investigation among researchers. To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head. In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. The experiments, conducted with GPT2 and TinyLLAMA, have allowed us to observe how certain information heads, relation heads, and Multilayer Perceptrons collaboratively encode knowledge within the model. Moreover, we evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies. Finally, we utilize knowledge circuits to analyze and interpret language model behaviors such as hallucinations and in-context learning. We believe the knowledge circuits hold potential for advancing our understanding of Transformers and guiding the improved design of knowledge editing. Code and data are available in https://github.com/zjunlp/KnowledgeCircuits.

Related papers

• Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models [20.157061521694096]
  This study investigates the differences between entity and relational knowledge through knowledge editing. To further elucidate the differences between entity and relational knowledge, we employ causal analysis to investigate how relational knowledge is stored in pre-trained models. This insight highlights the multifaceted nature of knowledge storage in language models, underscoring the complexity of manipulating specific types of knowledge within these models.
  arXiv  Detail & Related papers  (2024-09-01T05:09:11Z)
• 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)
• UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models [100.4659557650775]
  We propose a UNified knowledge inTERface, UNTER, to provide a unified perspective to exploit both structured knowledge and unstructured knowledge. With both forms of knowledge injected, UNTER gains continuous improvements on a series of knowledge-driven NLP tasks.
  arXiv  Detail & Related papers  (2023-05-02T17:33:28Z)
• LM-CORE: Language Models with Contextually Relevant External Knowledge [13.451001884972033]
  We argue that storing large amounts of knowledge in the model parameters is sub-optimal given the ever-growing amounts of knowledge and resource requirements. We present LM-CORE -- a general framework to achieve this -- that allows textitdecoupling of the language model training from the external knowledge source. Experimental results show that LM-CORE, having access to external knowledge, achieves significant and robust outperformance over state-of-the-art knowledge-enhanced language models on knowledge probing tasks.
  arXiv  Detail & Related papers  (2022-08-12T18:59:37Z)
• Understanding Knowledge Integration in Language Models with Graph Convolutions [28.306949176011763]
  knowledge integration (KI) methods aim to incorporate external knowledge into pretrained language models (LMs) This paper revisits the KI process in these models with an information-theoretic view and shows that KI can be interpreted using a graph convolution operation. We analyze two well-known knowledge-enhanced LMs: ERNIE and K-Adapter, and find that only a small amount of factual knowledge is integrated in them.
  arXiv  Detail & Related papers  (2022-02-02T11:23:36Z)
• Kformer: Knowledge Injection in Transformer Feed-Forward Layers [107.71576133833148]
  We propose a novel knowledge fusion model, namely Kformer, which incorporates external knowledge through the feed-forward layer in Transformer. We empirically find that simply injecting knowledge into FFN can facilitate the pre-trained language model's ability and facilitate current knowledge fusion methods.
  arXiv  Detail & Related papers  (2022-01-15T03:00:27Z)
• K-XLNet: A General Method for Combining Explicit Knowledge with Language Model Pretraining [5.178964604577459]
  We focus on improving model pretraining by leveraging explicit knowledge. To be specific, we first match knowledge facts from knowledge graph (KG) and then add a knowledge injunction layer to transformer directly. The experimental results show that solely by adding external knowledge to transformer can improve the learning performance on many NLP tasks.
  arXiv  Detail & Related papers  (2021-03-25T06:14:18Z)
• Towards a Universal Continuous Knowledge Base [49.95342223987143]
  We propose a method for building a continuous knowledge base that can store knowledge imported from multiple neural networks. Experiments on text classification show promising results. We import the knowledge from multiple models to the knowledge base, from which the fused knowledge is exported back to a single model.
  arXiv  Detail & Related papers  (2020-12-25T12:27:44Z)
• Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers [54.417299589288184]
  We investigate models for complementing the distributional knowledge of BERT with conceptual knowledge from ConceptNet and its corresponding Open Mind Common Sense (OMCS) corpus. Our adapter-based models substantially outperform BERT on inference tasks that require the type of conceptual knowledge explicitly present in ConceptNet and OMCS.
  arXiv  Detail & Related papers  (2020-05-24T15:49:57Z)

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.