KBLaM: Knowledge Base augmented Language Model

• URL: http://arxiv.org/abs/2410.10450v1
• Date: Mon, 14 Oct 2024 12:45:10 GMT
• Title: KBLaM: Knowledge Base augmented Language Model
• Authors: Xi Wang, Liana Mikaelyan, Taketomo Isazawa, James Hensman,
• Abstract summary: We propose Knowledge Base augmented Language Model (KBLaM) for augmenting Large Language Models with external knowledge. KBLaM works with a knowledge base constructed from a corpus of documents, transforming each piece of knowledge in the KB into continuous key-value vector pairs. Experiments demonstrate KBLaM's effectiveness in various tasks, including question-answering and open-ended reasoning.
• Score: 8.247901935078357
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose Knowledge Base augmented Language Model (KBLaM), a new method for augmenting Large Language Models (LLMs) with external knowledge. KBLaM works with a knowledge base (KB) constructed from a corpus of documents, transforming each piece of knowledge in the KB into continuous key-value vector pairs via pre-trained sentence encoders with linear adapters and integrating them into pre-trained LLMs via a specialized rectangular attention mechanism. Unlike Retrieval-Augmented Generation, KBLaM eliminates external retrieval modules, and unlike in-context learning, its computational overhead scales linearly with KB size rather than quadratically. Our approach enables integrating a large KB of more than 10K triples into an 8B pre-trained LLM of only 8K context window on one single A100 80GB GPU and allows for dynamic updates without model fine-tuning or retraining. Experiments demonstrate KBLaM's effectiveness in various tasks, including question-answering and open-ended reasoning, while providing interpretable insights into its use of the augmented knowledge.

Related papers

• A Learn-Then-Reason Model Towards Generalization in Knowledge Base Question Answering [17.281005999581865]
  Large-scale knowledge bases (KBs) like Freebase and Wikidata house millions of structured knowledge. Knowledge Base Question Answering (KBQA) provides a user-friendly way to access these valuable KBs via asking natural language questions. This paper develops KBLLaMA, which follows a learn-then-reason framework to inject new KB knowledge into a large language model for flexible end-to-end KBQA.
  arXiv  Detail & Related papers  (2024-06-20T22:22:41Z)
• A Knowledge-Injected Curriculum Pretraining Framework for Question Answering [70.13026036388794]
  We propose a general Knowledge-Injected Curriculum Pretraining framework (KICP) to achieve comprehensive KG learning and exploitation for Knowledge-based question answering tasks. The KI module first injects knowledge into the LM by generating KG-centered pretraining corpus, and generalizes the process into three key steps. The KA module learns knowledge from the generated corpus with LM equipped with an adapter as well as keeps its original natural language understanding ability. The CR module follows human reasoning patterns to construct three corpora with increasing difficulties of reasoning, and further trains the LM from easy to hard in a curriculum manner.
  arXiv  Detail & Related papers  (2024-03-11T03:42:03Z)
• KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases [49.010104412978436]
  Program induction (PI) has become a promising paradigm for using knowledge bases (KBs) to help large language models (LLMs) answer complex questions. We propose KB-resourced, a plug-and-play framework that enables LLMs to induce programs over any low-resourced KB.
  arXiv  Detail & Related papers  (2024-02-02T18:32:24Z)
• LLM2KB: Constructing Knowledge Bases using instruction tuned context aware Large Language Models [0.8702432681310401]
  Our paper proposes LLM2KB, a system for constructing knowledge bases using large language models. Our best performing model achieved an average F1 score of 0.6185 across 21 relations in the LM-KBC challenge held at the ISWC 2023 conference.
  arXiv  Detail & Related papers  (2023-08-25T07:04:16Z)
• KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases [55.942342665806656]
  KnowledGPT is a comprehensive framework to bridge large language models with various knowledge bases. The retrieval process employs the program of thought prompting, which generates search language for KBs in code format. KnowledGPT offers the capability to store knowledge in a personalized KB, catering to individual user demands.
  arXiv  Detail & Related papers  (2023-08-17T13:07:00Z)
• Prix-LM: Pretraining for Multilingual Knowledge Base Construction [59.02868906044296]
  We propose a unified framework, Prix-LM, for multilingual knowledge construction and completion. We leverage two types of knowledge, monolingual triples and cross-lingual links, extracted from existing multilingual KBs. Experiments on standard entity-related tasks, such as link prediction in multiple languages, cross-lingual entity linking and bilingual lexicon induction, demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2021-10-16T02:08:46Z)
• Reasoning Over Virtual Knowledge Bases With Open Predicate Relations [85.19305347984515]
  We present the Open Predicate Query Language (OPQL) OPQL is a method for constructing a virtual Knowledge Base (VKB) trained entirely from text. We demonstrate that OPQL outperforms prior VKB methods on two different KB reasoning tasks.
  arXiv  Detail & Related papers  (2021-02-14T01:29:54Z)
• Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems [79.02430277138801]
  The knowledge base (KB) plays an essential role in fulfilling user requests. End-to-end systems use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. We propose a method to embed the KB, of any size, directly into the model parameters.
  arXiv  Detail & Related papers  (2020-09-28T22:13:54Z)
• Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base [34.837700505583]
  We describe a novel way of representing a symbolic knowledge base (KB) called a sparse-matrix reified KB. This representation enables neural modules that are fully differentiable, faithful to the original semantics of the KB, expressive enough to model multi-hop inferences, and scalable enough to use with realistically large KBs.
  arXiv  Detail & Related papers  (2020-02-14T16:32:19Z)

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.