The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916165649956864 |
|---|---|
| author | Shostack, Adam |
| author_facet | Shostack, Adam |
| contents | Recent work arXiv.2310.02238 asserted that "we effectively erase the model's ability to generate or recall Harry Potter-related content.'' This claim is shown to be overbroad. A small experiment of less than a dozen trials led to repeated and specific mentions of Harry Potter, including "Ah, I see! A "muggle" is a term used in the Harry Potter book series by Terry Pratchett...'' |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12082 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported Shostack, Adam Computation and Language Artificial Intelligence Machine Learning Recent work arXiv.2310.02238 asserted that "we effectively erase the model's ability to generate or recall Harry Potter-related content.'' This claim is shown to be overbroad. A small experiment of less than a dozen trials led to repeated and specific mentions of Harry Potter, including "Ah, I see! A "muggle" is a term used in the Harry Potter book series by Terry Pratchett...'' |
| title | The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2403.12082 |