59 lines
1.8 KiB
Markdown
59 lines
1.8 KiB
Markdown
|
---
|
||
|
|
date: '2023-01-29T10:47:52'
|
||
|
|
hypothesis-meta:
|
||
|
|
created: '2023-01-29T10:47:52.638117+00:00'
|
||
|
|
document:
|
||
|
|
title:
|
||
|
|
- 2301.11305.pdf
|
||
|
|
flagged: false
|
||
|
|
group: __world__
|
||
|
|
hidden: false
|
||
|
|
id: YYCjTJ_CEe2thKdVH4ie0A
|
||
|
|
links:
|
||
|
|
html: https://hypothes.is/a/YYCjTJ_CEe2thKdVH4ie0A
|
||
|
|
incontext: https://hyp.is/YYCjTJ_CEe2thKdVH4ie0A/arxiv.org/pdf/2301.11305.pdf
|
||
|
|
json: https://hypothes.is/api/annotations/YYCjTJ_CEe2thKdVH4ie0A
|
||
|
|
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: 30225
|
||
|
|
start: 30062
|
||
|
|
type: TextPositionSelector
|
||
|
|
- exact: We simulate human re-vision by replacing 5 word spans of the text with
|
||
|
|
samplesfrom T5-3B until r% of the text has been replaced, andreport performance
|
||
|
|
as r varies.
|
||
|
|
prefix: 'n increasingly heavily revised. '
|
||
|
|
suffix: ' Figure 5 shows that De-tectGPT '
|
||
|
|
type: TextQuoteSelector
|
||
|
|
source: https://arxiv.org/pdf/2301.11305.pdf
|
||
|
|
text: I question the trustworthiness of this simulation - human edits are probably
|
||
|
|
going to be more sporadic and random.
|
||
|
|
updated: '2023-01-29T10:47:52.638117+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/2023/01/29/1674989272
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
<blockquote>We simulate human re-vision by replacing 5 word spans of the text with samplesfrom T5-3B until r% of the text has been replaced, andreport performance as r varies.</blockquote>I question the trustworthiness of this simulation - human edits are probably going to be more sporadic and random.
|