brainsteam.co.uk/brainsteam/content/annotations/2023/01/29/1674989465.md

2.3 KiB

date hypothesis-meta in-reply-to tags type url
2023-01-29T10:51:05
created document flagged group hidden id links permissions tags target text updated uri user user_info
2023-01-29T10:51:05.830376+00:00
title
2301.11305.pdf
false __world__ false 1KcQzJ_CEe26lwMlz8h5FA
html incontext json
https://hypothes.is/a/1KcQzJ_CEe26lwMlz8h5FA https://hyp.is/1KcQzJ_CEe26lwMlz8h5FA/arxiv.org/pdf/2301.11305.pdf https://hypothes.is/api/annotations/1KcQzJ_CEe26lwMlz8h5FA
admin delete read update
acct:ravenscroftj@hypothes.is
acct:ravenscroftj@hypothes.is
group:__world__
acct:ravenscroftj@hypothes.is
chatgpt
detecting gpt
selector source
end start type
39629 39349 TextPositionSelector
exact prefix suffix type
hile in this work, we use off-the-shelfmask-filling models such as T5 and mT5 (for non-Englishlanguages), some domains may see reduced performanceif existing mask-filling models do not well represent thespace of meaningful rephrases, reducing the quality of thecurvature estimate. onable pertur-bation function. W While DetectGPT provides the be TextQuoteSelector
https://arxiv.org/pdf/2301.11305.pdf
The approach requires access to language models that can meaningfully and accurately rephrase (perturbate) the outputs from the model under evaluation. If these things do not align then it may not work well. 2023-01-29T10:51:05.830376+00:00 https://arxiv.org/pdf/2301.11305.pdf acct:ravenscroftj@hypothes.is
display_name
James Ravenscroft
https://arxiv.org/pdf/2301.11305.pdf
chatgpt
detecting gpt
hypothesis
annotation /annotations/2023/01/29/1674989465
hile in this work, we use off-the-shelfmask-filling models such as T5 and mT5 (for non-Englishlanguages), some domains may see reduced performanceif existing mask-filling models do not well represent thespace of meaningful rephrases, reducing the quality of thecurvature estimate.
The approach requires access to language models that can meaningfully and accurately rephrase (perturbate) the outputs from the model under evaluation. If these things do not align then it may not work well.