Learn and Unlearn: Addressing Misinformation in Multilingual LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911135165317120 |
|---|---|
| author | Lu, Taiming Koehn, Philipp |
| author_facet | Lu, Taiming Koehn, Philipp |
| contents | This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in, once introduced into these models through training data, can spread across different languages, compromising the integrity and reliability of the generated content. Our findings reveal that standard unlearning techniques, which typically focus on English data, are insufficient in mitigating the spread of harmful content in multilingual contexts and could inadvertently reinforce harmful content across languages. We show that only by addressing harmful responses in both English and the original language of the harmful data can we effectively eliminate generations for all languages. This underscores the critical need for comprehensive unlearning strategies that consider the multilingual nature of modern LLMs to enhance their safety and reliability across diverse linguistic landscapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learn and Unlearn: Addressing Misinformation in Multilingual LLMs Lu, Taiming Koehn, Philipp Computation and Language Machine Learning This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in, once introduced into these models through training data, can spread across different languages, compromising the integrity and reliability of the generated content. Our findings reveal that standard unlearning techniques, which typically focus on English data, are insufficient in mitigating the spread of harmful content in multilingual contexts and could inadvertently reinforce harmful content across languages. We show that only by addressing harmful responses in both English and the original language of the harmful data can we effectively eliminate generations for all languages. This underscores the critical need for comprehensive unlearning strategies that consider the multilingual nature of modern LLMs to enhance their safety and reliability across diverse linguistic landscapes. |
| title | Learn and Unlearn: Addressing Misinformation in Multilingual LLMs |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2406.13748 |