Add 'brainsteam/content/annotations/2023/01/29/1674989184.md'

brainsteam/content/annotations/2023/01/29/1674989184.md

@@ -0,0 +1,62 @@
+---
+date: '2023-01-29T10:46:24'
+hypothesis-meta:
+  created: '2023-01-29T10:46:24.271948+00:00'
+  document:
+    title:
+    - 2301.11305.pdf
+  flagged: false
+  group: __world__
+  hidden: false
+  id: LNKuap_CEe2NNLuZfhdxTA
+  links:
+    html: https://hypothes.is/a/LNKuap_CEe2NNLuZfhdxTA
+    incontext: https://hyp.is/LNKuap_CEe2NNLuZfhdxTA/arxiv.org/pdf/2301.11305.pdf
+    json: https://hypothes.is/api/annotations/LNKuap_CEe2NNLuZfhdxTA
+  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: 31791
+      start: 31366
+      type: TextPositionSelector
+    - exact: Figure 5. We simulate human edits to machine-generated text byreplacing
+        varying fractions of model samples with T5-3B gener-ated text (masking out
+        random five word spans until r% of text ismasked to simulate human edits to
+        machine-generated text). Thefour top-performing methods all generally degrade
+        in performancewith heavier revision, but DetectGPT is consistently most accurate.Experiment
+        is conducted on the XSum dataset
+      prefix: etectGPTLogRankLikelihoodEntropy
+      suffix: .XSum SQuAD WritingPromptsMethod
+      type: TextQuoteSelector
+    source: https://arxiv.org/pdf/2301.11305.pdf
+  text: DetectGPT shows 95% AUROC for texts that have been modified by about 10% and
+    this drops off to about 85% when text is changed up to 24%.
+  updated: '2023-01-29T10:46:24.271948+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/2023/01/29/1674989184
+
+---
+
+
+
+ <blockquote>Figure 5. We simulate human edits to machine-generated text byreplacing varying fractions of model samples with T5-3B gener-ated text (masking out random five word spans until r% of text ismasked to simulate human edits to machine-generated text). Thefour top-performing methods all generally degrade in performancewith heavier revision, but DetectGPT is consistently most accurate.Experiment is conducted on the XSum dataset</blockquote>DetectGPT shows 95% AUROC for texts that have been modified by about 10% and this drops off to about 85% when text is changed up to 24%.