Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting
Top Cited Papers
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (16) , 18126-18134
Abstract
Incorporating factual knowledge in knowledge graph is regarded as a promising approach for mitigating the hallucination of large language models (LLMs). Existing methods usually only use the user's input to query the knowledge graph, thus failing to address the factual hallucination generated by LLMs during its reasoning process. To address this problem, this paper proposes Knowledge Graph-based Retrofitting (KGR), a new framework that incorporates LLMs with KGs to mitigate factual hallucination during the reasoning process by retrofitting the initial draft responses of LLMs based on the factual knowledge stored in KGs. Specifically, KGR leverages LLMs to extract, select, validate, and retrofit factual statements within the model-generated responses, which enables an autonomous knowledge verifying and refining procedure without any additional manual efforts. Experiments show that KGR can significantly improve the performance of LLMs on factual QA benchmarks especially when involving complex reasoning processes, which demonstrates the necessity and effectiveness of KGR in mitigating hallucination and enhancing the reliability of LLMs.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Lost in the Middle: How Language Models Use Long ContextsTransactions of the Association for Computational Linguistics, 2024
- WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data2023
- RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding2023
- The Web Can Be Your Oyster for Improving Language Models2023
- DKPLM: Decomposable Knowledge-Enhanced Pre-trained Language Model for Natural Language UnderstandingProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric ViewProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Improved Natural Language Generation via Loss Truncation2020
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering2018