diff --git a/brainsteam/content/annotations/2023/01/29/1674988556.md b/brainsteam/content/annotations/2023/01/29/1674988556.md new file mode 100644 index 0000000..1fc41ff --- /dev/null +++ b/brainsteam/content/annotations/2023/01/29/1674988556.md @@ -0,0 +1,61 @@ +--- +date: '2023-01-29T10:35:56' +hypothesis-meta: + created: '2023-01-29T10:35:56.649264+00:00' + document: + title: + - 2301.11305.pdf + flagged: false + group: __world__ + hidden: false + id: tr0lTp_AEe2k81d5ilJ0Xw + links: + html: https://hypothes.is/a/tr0lTp_AEe2k81d5ilJ0Xw + incontext: https://hyp.is/tr0lTp_AEe2k81d5ilJ0Xw/arxiv.org/pdf/2301.11305.pdf + json: https://hypothes.is/api/annotations/tr0lTp_AEe2k81d5ilJ0Xw + 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: 1096 + start: 756 + type: TextPositionSelector + - exact: his approach, which we call DetectGPT,does not require training a separate + classifier, col-lecting a dataset of real or generated passages, orexplicitly + watermarking generated text. It usesonly log probabilities computed by the + model ofinterest and random perturbations of the passagefrom another generic + pre-trained language model(e.g, T5) + prefix: ' is generated from a givenLLM. T' + suffix: . We find DetectGPT is more disc + type: TextQuoteSelector + source: https://arxiv.org/pdf/2301.11305.pdf + text: The novelty of this approach is that it is cheap to set up as long as you + have the log probabilities generated by the model of interest. + updated: '2023-01-29T10:35:56.649264+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/2023/01/29/1674988556 + +--- + + + +
his approach, which we call DetectGPT,does not require training a separate classifier, col-lecting a dataset of real or generated passages, orexplicitly watermarking generated text. It usesonly log probabilities computed by the model ofinterest and random perturbations of the passagefrom another generic pre-trained language model(e.g, T5)The novelty of this approach is that it is cheap to set up as long as you have the log probabilities generated by the model of interest. \ No newline at end of file