Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913266994774016 |
|---|---|
| author | Agrawal, Garima Kumarage, Tharindu Alghamdi, Zeyad Liu, Huan |
| author_facet | Agrawal, Garima Kumarage, Tharindu Alghamdi, Zeyad Liu, Huan |
| contents | The contemporary LLMs are prone to producing hallucinations, stemming mainly from the knowledge gaps within the models. To address this critical limitation, researchers employ diverse strategies to augment the LLMs by incorporating external knowledge, aiming to reduce hallucinations and enhance reasoning accuracy. Among these strategies, leveraging knowledge graphs as a source of external information has demonstrated promising results. In this survey, we comprehensively review these knowledge-graph-based augmentation techniques in LLMs, focusing on their efficacy in mitigating hallucinations. We systematically categorize these methods into three overarching groups, offering methodological comparisons and performance evaluations. Lastly, this survey explores the current trends and challenges associated with these techniques and outlines potential avenues for future research in this emerging field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_07914 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey Agrawal, Garima Kumarage, Tharindu Alghamdi, Zeyad Liu, Huan Computation and Language Machine Learning The contemporary LLMs are prone to producing hallucinations, stemming mainly from the knowledge gaps within the models. To address this critical limitation, researchers employ diverse strategies to augment the LLMs by incorporating external knowledge, aiming to reduce hallucinations and enhance reasoning accuracy. Among these strategies, leveraging knowledge graphs as a source of external information has demonstrated promising results. In this survey, we comprehensively review these knowledge-graph-based augmentation techniques in LLMs, focusing on their efficacy in mitigating hallucinations. We systematically categorize these methods into three overarching groups, offering methodological comparisons and performance evaluations. Lastly, this survey explores the current trends and challenges associated with these techniques and outlines potential avenues for future research in this emerging field. |
| title | Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2311.07914 |