FLAME: Empowering Frozen LLMs for Knowledge Graph Completion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Bo, Xu, Yi, Ma, Bolei, Song, Yunchong, Ding, Jiaxin, Fu, Luoyi, Wang, Xinbing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908794732150784
author Xue, Bo
Xu, Yi
Ma, Bolei
Song, Yunchong
Ding, Jiaxin
Fu, Luoyi
Wang, Xinbing
author_facet Xue, Bo
Xu, Yi
Ma, Bolei
Song, Yunchong
Ding, Jiaxin
Fu, Luoyi
Wang, Xinbing
contents Traditional knowledge graph completion (KGC) methods rely solely on structural information and struggle with sparsity, while Large Language Models (LLMs) address these limitations through rich world knowledge and strong context modeling. Fine-tuning LLMs is effective but costly, while non-fine-tuned LLMs are efficient but suboptimal. To address this trade-off, we propose \textbf{FLAME}, a framework that extracts context-aware hidden states from intermediate layers of frozen LLMs to train data-efficient KGC classifiers. We bridge LLM-KG semantic gaps via subgraph-based entity descriptions and employ sliced mutual information (SMI) to quantify task-relevant information in representations. Experiments demonstrate that FLAME achieves 47\% improvement over non-fine-tuned LLM baselines and, to our knowledge, is the first to achieve fine-tuned performance with $188\times$ memory efficiency and $26.11\times$ speedup.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06787
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FLAME: Empowering Frozen LLMs for Knowledge Graph Completion
Xue, Bo
Xu, Yi
Ma, Bolei
Song, Yunchong
Ding, Jiaxin
Fu, Luoyi
Wang, Xinbing
Computation and Language
Traditional knowledge graph completion (KGC) methods rely solely on structural information and struggle with sparsity, while Large Language Models (LLMs) address these limitations through rich world knowledge and strong context modeling. Fine-tuning LLMs is effective but costly, while non-fine-tuned LLMs are efficient but suboptimal. To address this trade-off, we propose \textbf{FLAME}, a framework that extracts context-aware hidden states from intermediate layers of frozen LLMs to train data-efficient KGC classifiers. We bridge LLM-KG semantic gaps via subgraph-based entity descriptions and employ sliced mutual information (SMI) to quantify task-relevant information in representations. Experiments demonstrate that FLAME achieves 47\% improvement over non-fine-tuned LLM baselines and, to our knowledge, is the first to achieve fine-tuned performance with $188\times$ memory efficiency and $26.11\times$ speedup.
title FLAME: Empowering Frozen LLMs for Knowledge Graph Completion
topic Computation and Language
url https://arxiv.org/abs/2408.06787