Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929432247140352 |
|---|---|
| author | Liu, Yang Tian, Xiaobin Sun, Zequn Hu, Wei |
| author_facet | Liu, Yang Tian, Xiaobin Sun, Zequn Hu, Wei |
| contents | Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of LLMs to KG entities, which inevitably brings errors. In this paper, we present a finetuning framework, DIFT, aiming to unleash the KG completion ability of LLMs and avoid grounding errors. Given an incomplete fact, DIFT employs a lightweight model to obtain candidate entities and finetunes an LLM with discrimination instructions to select the correct one from the given candidates. To improve performance while reducing instruction data, DIFT uses a truncated sampling method to select useful facts for finetuning and injects KG embeddings into the LLM. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16127 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion Liu, Yang Tian, Xiaobin Sun, Zequn Hu, Wei Computation and Language Artificial Intelligence Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of LLMs to KG entities, which inevitably brings errors. In this paper, we present a finetuning framework, DIFT, aiming to unleash the KG completion ability of LLMs and avoid grounding errors. Given an incomplete fact, DIFT employs a lightweight model to obtain candidate entities and finetunes an LLM with discrimination instructions to select the correct one from the given candidates. To improve performance while reducing instruction data, DIFT uses a truncated sampling method to select useful facts for finetuning and injects KG embeddings into the LLM. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed framework. |
| title | Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.16127 |