Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912182966419456 |
|---|---|
| author | Cho, Eunjung Cho, Won Ik Seo, Soomin |
| author_facet | Cho, Eunjung Cho, Won Ik Seo, Soomin |
| contents | Hallucination in large language models (LLMs) remains a significant challenge for their safe deployment, particularly due to its potential to spread misinformation. Most existing solutions address this challenge by focusing on aligning the models with credible sources or by improving how models communicate their confidence (or lack thereof) in their outputs. While these measures may be effective in most contexts, they may fall short in scenarios requiring more nuanced approaches, especially in situations where access to accurate data is limited or determining credible sources is challenging. In this study, we take North Korea - a country characterised by an extreme lack of reliable sources and the prevalence of sensationalist falsehoods - as a case study. We explore and evaluate how some of the best-performing multilingual LLMs and specific language-based models generate information about North Korea in three languages spoken in countries with significant geo-political interests: English (United States, United Kingdom), Korean (South Korea), and Mandarin Chinese (China). Our findings reveal significant differences, suggesting that the choice of model and language can lead to vastly different understandings of North Korea, which has important implications given the global security challenges the country poses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05981 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea Cho, Eunjung Cho, Won Ik Seo, Soomin Computation and Language Hallucination in large language models (LLMs) remains a significant challenge for their safe deployment, particularly due to its potential to spread misinformation. Most existing solutions address this challenge by focusing on aligning the models with credible sources or by improving how models communicate their confidence (or lack thereof) in their outputs. While these measures may be effective in most contexts, they may fall short in scenarios requiring more nuanced approaches, especially in situations where access to accurate data is limited or determining credible sources is challenging. In this study, we take North Korea - a country characterised by an extreme lack of reliable sources and the prevalence of sensationalist falsehoods - as a case study. We explore and evaluate how some of the best-performing multilingual LLMs and specific language-based models generate information about North Korea in three languages spoken in countries with significant geo-political interests: English (United States, United Kingdom), Korean (South Korea), and Mandarin Chinese (China). Our findings reveal significant differences, suggesting that the choice of model and language can lead to vastly different understandings of North Korea, which has important implications given the global security challenges the country poses. |
| title | Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.05981 |