diff --git a/brainsteam/content/annotations/2023/01/29/1674989603.md b/brainsteam/content/annotations/2023/01/29/1674989603.md new file mode 100644 index 0000000..b11f409 --- /dev/null +++ b/brainsteam/content/annotations/2023/01/29/1674989603.md @@ -0,0 +1,60 @@ +--- +date: '2023-01-29T10:53:23' +hypothesis-meta: + created: '2023-01-29T10:53:23.198884+00:00' + document: + title: + - 2301.11305.pdf + flagged: false + group: __world__ + hidden: false + id: JoZDmp_DEe2QSbcSZI0WEA + links: + html: https://hypothes.is/a/JoZDmp_DEe2QSbcSZI0WEA + incontext: https://hyp.is/JoZDmp_DEe2QSbcSZI0WEA/arxiv.org/pdf/2301.11305.pdf + json: https://hypothes.is/api/annotations/JoZDmp_DEe2QSbcSZI0WEA + permissions: + admin: + - acct:ravenscroftj@hypothes.is + delete: + - acct:ravenscroftj@hypothes.is + read: + - group:__world__ + update: + - acct:ravenscroftj@hypothes.is + tags: + - chatgpt + - detecting gpt + target: + - selector: + - end: 27924 + start: 27657 + type: TextPositionSelector + - exact: We find that supervised detectors can provide similardetection performance + to DetectGPT on in-distribution datalike English news, but perform significantly + worse than zero-shot methods in the case of English scientific writing andfail + altogether for German writing. T + prefix: 'm each dataset for evalua-tion. ' + suffix: his finding echoes pastwork show + type: TextQuoteSelector + source: https://arxiv.org/pdf/2301.11305.pdf + text: supervised detection methods fail on out of domain examples whereas detectgpt + seems to be robust to changes in domain. + updated: '2023-01-29T10:53:23.198884+00:00' + uri: https://arxiv.org/pdf/2301.11305.pdf + user: acct:ravenscroftj@hypothes.is + user_info: + display_name: James Ravenscroft +in-reply-to: https://arxiv.org/pdf/2301.11305.pdf +tags: +- chatgpt +- detecting gpt +- hypothesis +type: annotation +url: /annotations/2023/01/29/1674989603 + +--- + + + +
We find that supervised detectors can provide similardetection performance to DetectGPT on in-distribution datalike English news, but perform significantly worse than zero-shot methods in the case of English scientific writing andfail altogether for German writing. Tsupervised detection methods fail on out of domain examples whereas detectgpt seems to be robust to changes in domain. \ No newline at end of file