SKILL: Structured Knowledge Infusion for Large Language Models

• URL: http://arxiv.org/abs/2205.08184v1
• Date: Tue, 17 May 2022 09:12:22 GMT
• Title: SKILL: Structured Knowledge Infusion for Large Language Models
• Authors: Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi
• Abstract summary: We propose a method to infuse structured knowledge into large language models (LLMs) We show that models pre-trained on Wikidata KG with our method outperform the T5 baselines on FreebaseQA and WikiHop. We saw 3x improvement of exact match score on MetaQA task compared to T5 baseline.
• Score: 46.34209061364282
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better internalize knowledge from a structured data, such as a knowledge graph, or from text. In this work, we propose a method to infuse structured knowledge into LLMs, by directly training T5 models on factual triples of knowledge graphs (KGs). We show that models pre-trained on Wikidata KG with our method outperform the T5 baselines on FreebaseQA and WikiHop, as well as the Wikidata-answerable subset of TriviaQA and NaturalQuestions. The models pre-trained on factual triples compare competitively with the ones on natural language sentences that contain the same knowledge. Trained on a smaller size KG, WikiMovies, we saw 3x improvement of exact match score on MetaQA task compared to T5 baseline. The proposed method has an advantage that no alignment between the knowledge graph and text corpus is required in curating training data. This makes our method particularly useful when working with industry-scale knowledge graphs.

Related papers

• Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
  We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
  arXiv  Detail & Related papers  (2024-03-26T06:57:23Z)
• Deep Bidirectional Language-Knowledge Graph Pretraining [159.9645181522436]
  DRAGON is a self-supervised approach to pretraining a deeply joint language-knowledge foundation model from text and KG at scale. Our model takes pairs of text segments and relevant KG subgraphs as input and bidirectionally fuses information from both modalities.
  arXiv  Detail & Related papers  (2022-10-17T18:02:52Z)
• Joint Language Semantic and Structure Embedding for Knowledge Graph Completion [66.15933600765835]
  We propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information. Our method embeds knowledge graphs for the completion task via fine-tuning pre-trained language models. Our experiments on a variety of knowledge graph benchmarks have demonstrated the state-of-the-art performance of our method.
  arXiv  Detail & Related papers  (2022-09-19T02:41:02Z)
• From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer [41.69537736842654]
  We provide an approach GenKGC, which converts knowledge graph completion to sequence-to-sequence generation task with the pre-trained language model. We introduce relation-guided demonstration and entity-aware hierarchical decoding for better representation learning and fast inference. We also release a new large-scale Chinese knowledge graph dataset AliopenKG500 for research purpose.
  arXiv  Detail & Related papers  (2022-02-04T12:52:32Z)
• Calculating Question Similarity is Enough:A New Method for KBQA Tasks [8.056701645706404]
  This paper proposes a Corpus Generation - Retrieve Method (CGRM) with Pre-training Language Model (PLM) and Knowledge Graph (KG) Firstly, based on the mT5 model, we designed two new pre-training tasks: knowledge masked language modeling and question generation based on the paragraph. Secondly, after preprocessing triples of knowledge graph with a series of rules, the kT5 model generates natural language QA pairs based on processed triples.
  arXiv  Detail & Related papers  (2021-11-15T10:31:46Z)
• Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models [42.38563175680914]
  This paper studies how to automatically generate a natural language text that describes the facts in knowledge graph (KG) Considering the few-shot setting, we leverage the excellent capacities of pretrained language models (PLMs) in language understanding and generation.
  arXiv  Detail & Related papers  (2021-06-03T06:48:00Z)
• ALICE: Active Learning with Contrastive Natural Language Explanations [69.03658685761538]
  We propose Active Learning with Contrastive Explanations (ALICE) to improve data efficiency in learning. ALICE learns to first use active learning to select the most informative pairs of label classes to elicit contrastive natural language explanations. It extracts knowledge from these explanations using a semantically extracted knowledge.
  arXiv  Detail & Related papers  (2020-09-22T01:02:07Z)
• Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning [73.0598186896953]
  We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training.
  arXiv  Detail & Related papers  (2020-04-29T14:22:42Z)

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.