LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910903331454976 |
|---|---|
| author | Ao, Tu Yu, Yanhua Wang, Yuling Deng, Yang Guo, Zirui Pang, Liang Wang, Pinghui Chua, Tat-Seng Zhang, Xiao Cai, Zhen |
| author_facet | Ao, Tu Yu, Yanhua Wang, Yuling Deng, Yang Guo, Zirui Pang, Liang Wang, Pinghui Chua, Tat-Seng Zhang, Xiao Cai, Zhen |
| contents | Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning. However, delays in knowledge updates may cause them to reason incorrectly or produce harmful results. Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs by structurally organizing and connecting a wide range of entities and relations. Existing KG-based LLM reasoning methods only inject KGs' knowledge into prompts in a textual form, ignoring its structural information. Moreover, they mostly rely on close-source models or open-source models with large parameters, which poses challenges to high resource consumption. To address this, we propose a novel Lightweight and efficient Prompt learning-ReasOning Framework for KGQA (LightPROF), which leverages the full potential of LLMs to tackle complex reasoning tasks in a parameter-efficient manner. Specifically, LightPROF follows a "Retrieve-Embed-Reason process", first accurately, and stably retrieving the corresponding reasoning graph from the KG through retrieval module. Next, through a Transformer-based Knowledge Adapter, it finely extracts and integrates factual and structural information from the KG, then maps this information to the LLM's token embedding space, creating an LLM-friendly prompt to be used by the LLM for the final reasoning. Additionally, LightPROF only requires training Knowledge Adapter and can be compatible with any open-source LLM. Extensive experiments on two public KGQA benchmarks demonstrate that LightPROF achieves superior performance with small-scale LLMs. Furthermore, LightPROF shows significant advantages in terms of input token count and reasoning time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03137 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph Ao, Tu Yu, Yanhua Wang, Yuling Deng, Yang Guo, Zirui Pang, Liang Wang, Pinghui Chua, Tat-Seng Zhang, Xiao Cai, Zhen Artificial Intelligence Computation and Language Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning. However, delays in knowledge updates may cause them to reason incorrectly or produce harmful results. Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs by structurally organizing and connecting a wide range of entities and relations. Existing KG-based LLM reasoning methods only inject KGs' knowledge into prompts in a textual form, ignoring its structural information. Moreover, they mostly rely on close-source models or open-source models with large parameters, which poses challenges to high resource consumption. To address this, we propose a novel Lightweight and efficient Prompt learning-ReasOning Framework for KGQA (LightPROF), which leverages the full potential of LLMs to tackle complex reasoning tasks in a parameter-efficient manner. Specifically, LightPROF follows a "Retrieve-Embed-Reason process", first accurately, and stably retrieving the corresponding reasoning graph from the KG through retrieval module. Next, through a Transformer-based Knowledge Adapter, it finely extracts and integrates factual and structural information from the KG, then maps this information to the LLM's token embedding space, creating an LLM-friendly prompt to be used by the LLM for the final reasoning. Additionally, LightPROF only requires training Knowledge Adapter and can be compatible with any open-source LLM. Extensive experiments on two public KGQA benchmarks demonstrate that LightPROF achieves superior performance with small-scale LLMs. Furthermore, LightPROF shows significant advantages in terms of input token count and reasoning time. |
| title | LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2504.03137 |