Document (#43838)

Title

ChatGPT : Optimizing language models for dalogue

Issue

[30.11.2022].

Source

https://openai.com/blog/chatgpt/

Year

2022

Abstract

We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests. ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response.

Content

Zugang unter: https://chat.openai.com.

Theme

Computerlinguistik

Object

ChatGPT

Similar documents (content)

1. Lund, B.D.: ¬A brief review of ChatGPT : its value and the underlying GPT technology (2023) 0.22

   0.22365764 = sum of:
     0.22365764 = product of:
       1.1182882 = sum of:
         0.009566195 = weight(abstract_txt:which in 1874) [ClassicSimilarity], result of:
           0.009566195 = score(doc=1874,freq=1.0), product of:
             0.042023387 = queryWeight, product of:
               1.0522604 = boost
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.013705967 = queryNorm
             0.2276398 = fieldWeight in 1874, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.078125 = fieldNorm(doc=1874)
         0.09070043 = weight(abstract_txt:requests in 1874) [ClassicSimilarity], result of:
           0.09070043 = score(doc=1874,freq=2.0), product of:
             0.11859084 = queryWeight, product of:
               1.2499374 = boost
               6.922344 = idf(docFreq=118, maxDocs=44421)
               0.013705967 = queryNorm
             0.7648182 = fieldWeight in 1874, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.922344 = idf(docFreq=118, maxDocs=44421)
               0.078125 = fieldNorm(doc=1874)
         0.024430053 = weight(abstract_txt:model in 1874) [ClassicSimilarity], result of:
           0.024430053 = score(doc=1874,freq=1.0), product of:
             0.07851414 = queryWeight, product of:
               1.438307 = boost
               3.9827821 = idf(docFreq=2249, maxDocs=44421)
               0.013705967 = queryNorm
             0.31115484 = fieldWeight in 1874, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9827821 = idf(docFreq=2249, maxDocs=44421)
               0.078125 = fieldNorm(doc=1874)
         0.1353541 = weight(abstract_txt:trained in 1874) [ClassicSimilarity], result of:
           0.1353541 = score(doc=1874,freq=1.0), product of:
             0.2458362 = queryWeight, product of:
               2.5450752 = boost
               7.0475073 = idf(docFreq=104, maxDocs=44421)
               0.013705967 = queryNorm
             0.5505865 = fieldWeight in 1874, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.0475073 = idf(docFreq=104, maxDocs=44421)
               0.078125 = fieldNorm(doc=1874)
         0.8582374 = weight(abstract_txt:chatgpt in 1874) [ClassicSimilarity], result of:
           0.8582374 = score(doc=1874,freq=5.0), product of:
             0.62052107 = queryWeight, product of:
               5.718353 = boost
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.013705967 = queryNorm
             1.3830914 = fieldWeight in 1874, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.078125 = fieldNorm(doc=1874)
       0.2 = coord(5/25)
   

2. Aydin, Ö.; Karaarslan, E.: OpenAI ChatGPT generated literature review: : digital twin in healthcare (2022) 0.21

   0.2141655 = sum of:
     0.2141655 = product of:
       1.0708275 = sum of:
         0.008117186 = weight(abstract_txt:which in 1852) [ClassicSimilarity], result of:
           0.008117186 = score(doc=1852,freq=2.0), product of:
             0.042023387 = queryWeight, product of:
               1.0522604 = boost
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.013705967 = queryNorm
             0.19315878 = fieldWeight in 1852, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.046875 = fieldNorm(doc=1852)
         0.025388457 = weight(abstract_txt:model in 1852) [ClassicSimilarity], result of:
           0.025388457 = score(doc=1852,freq=3.0), product of:
             0.07851414 = queryWeight, product of:
               1.438307 = boost
               3.9827821 = idf(docFreq=2249, maxDocs=44421)
               0.013705967 = queryNorm
             0.3233616 = fieldWeight in 1852, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.9827821 = idf(docFreq=2249, maxDocs=44421)
               0.046875 = fieldNorm(doc=1852)
         0.06633805 = weight(abstract_txt:conversational in 1852) [ClassicSimilarity], result of:
           0.06633805 = score(doc=1852,freq=1.0), product of:
             0.17050189 = queryWeight, product of:
               1.4987434 = boost
               8.30027 = idf(docFreq=29, maxDocs=44421)
               0.013705967 = queryNorm
             0.38907516 = fieldWeight in 1852, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.30027 = idf(docFreq=29, maxDocs=44421)
               0.046875 = fieldNorm(doc=1852)
         0.14066409 = weight(abstract_txt:trained in 1852) [ClassicSimilarity], result of:
           0.14066409 = score(doc=1852,freq=3.0), product of:
             0.2458362 = queryWeight, product of:
               2.5450752 = boost
               7.0475073 = idf(docFreq=104, maxDocs=44421)
               0.013705967 = queryNorm
             0.57218623 = fieldWeight in 1852, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.0475073 = idf(docFreq=104, maxDocs=44421)
               0.046875 = fieldNorm(doc=1852)
         0.83031976 = weight(abstract_txt:chatgpt in 1852) [ClassicSimilarity], result of:
           0.83031976 = score(doc=1852,freq=13.0), product of:
             0.62052107 = queryWeight, product of:
               5.718353 = boost
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.013705967 = queryNorm
             1.3381008 = fieldWeight in 1852, product of:
               3.6055512 = tf(freq=13.0), with freq of:
                 13.0 = termFreq=13.0
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.046875 = fieldNorm(doc=1852)
       0.2 = coord(5/25)
   

3. Lund, B.D.; Wang, T.; Mannuru, N.R.; Nie, B.; Shimray, S.; Wang, Z.: ChatGPT and a new academic reality : artificial Intelligence-written research papers and the ethics of the large language models in scholarly publishing (2023) 0.20

   0.20022324 = sum of:
     0.20022324 = product of:
       1.0011162 = sum of:
         0.009566195 = weight(abstract_txt:which in 1944) [ClassicSimilarity], result of:
           0.009566195 = score(doc=1944,freq=1.0), product of:
             0.042023387 = queryWeight, product of:
               1.0522604 = boost
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.013705967 = queryNorm
             0.2276398 = fieldWeight in 1944, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.9137893 = idf(docFreq=6552, maxDocs=44421)
               0.078125 = fieldNorm(doc=1944)
         0.06413489 = weight(abstract_txt:requests in 1944) [ClassicSimilarity], result of:
           0.06413489 = score(doc=1944,freq=1.0), product of:
             0.11859084 = queryWeight, product of:
               1.2499374 = boost
               6.922344 = idf(docFreq=118, maxDocs=44421)
               0.013705967 = queryNorm
             0.54080814 = fieldWeight in 1944, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.922344 = idf(docFreq=118, maxDocs=44421)
               0.078125 = fieldNorm(doc=1944)
         0.024430053 = weight(abstract_txt:model in 1944) [ClassicSimilarity], result of:
           0.024430053 = score(doc=1944,freq=1.0), product of:
             0.07851414 = queryWeight, product of:
               1.438307 = boost
               3.9827821 = idf(docFreq=2249, maxDocs=44421)
               0.013705967 = queryNorm
             0.31115484 = fieldWeight in 1944, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.9827821 = idf(docFreq=2249, maxDocs=44421)
               0.078125 = fieldNorm(doc=1944)
         0.1353541 = weight(abstract_txt:trained in 1944) [ClassicSimilarity], result of:
           0.1353541 = score(doc=1944,freq=1.0), product of:
             0.2458362 = queryWeight, product of:
               2.5450752 = boost
               7.0475073 = idf(docFreq=104, maxDocs=44421)
               0.013705967 = queryNorm
             0.5505865 = fieldWeight in 1944, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.0475073 = idf(docFreq=104, maxDocs=44421)
               0.078125 = fieldNorm(doc=1944)
         0.7676309 = weight(abstract_txt:chatgpt in 1944) [ClassicSimilarity], result of:
           0.7676309 = score(doc=1944,freq=4.0), product of:
             0.62052107 = queryWeight, product of:
               5.718353 = boost
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.013705967 = queryNorm
             1.2370746 = fieldWeight in 1944, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.078125 = fieldNorm(doc=1944)
       0.2 = coord(5/25)
   

4. Hommen, D.L.: Collective intentionality and the structure of scientific theories (2007) 0.10

   0.098256744 = sum of:
     0.098256744 = product of:
       2.4564188 = sum of:
         2.4564188 = weight(abstract_txt:chatgpt in 1849) [ClassicSimilarity], result of:
           2.4564188 = score(doc=1849,freq=1.0), product of:
             0.62052107 = queryWeight, product of:
               5.718353 = boost
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.013705967 = queryNorm
             3.958639 = fieldWeight in 1849, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.917278 = idf(docFreq=43, maxDocs=44421)
               0.5 = fieldNorm(doc=1849)
       0.04 = coord(1/25)
   

5. Zhang, Y.; Ren, P.; Rijke, M. de: ¬A taxonomy, data set, and benchmark for detecting and classifying malevolent dialogue responses (2021) 0.08

   0.0823521 = sum of:
     0.0823521 = product of:
       0.51470065 = sum of:
         0.03915694 = weight(abstract_txt:response in 1357) [ClassicSimilarity], result of:
           0.03915694 = score(doc=1357,freq=1.0), product of:
             0.08534814 = queryWeight, product of:
               1.0603756 = boost
               5.872522 = idf(docFreq=339, maxDocs=44421)
               0.013705967 = queryNorm
             0.45879078 = fieldWeight in 1357, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.872522 = idf(docFreq=339, maxDocs=44421)
               0.078125 = fieldNorm(doc=1357)
         0.18107808 = weight(abstract_txt:dialogue in 1357) [ClassicSimilarity], result of:
           0.18107808 = score(doc=1357,freq=5.0), product of:
             0.13854009 = queryWeight, product of:
               1.3509847 = boost
               7.48196 = idf(docFreq=67, maxDocs=44421)
               0.013705967 = queryNorm
             1.3070446 = fieldWeight in 1357, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.48196 = idf(docFreq=67, maxDocs=44421)
               0.078125 = fieldNorm(doc=1357)
         0.13810535 = weight(abstract_txt:inappropriate in 1357) [ClassicSimilarity], result of:
           0.13810535 = score(doc=1357,freq=2.0), product of:
             0.15695864 = queryWeight, product of:
               1.4379882 = boost
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.013705967 = queryNorm
             0.8798837 = fieldWeight in 1357, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.078125 = fieldNorm(doc=1357)
         0.15636028 = weight(abstract_txt:conversational in 1357) [ClassicSimilarity], result of:
           0.15636028 = score(doc=1357,freq=2.0), product of:
             0.17050189 = queryWeight, product of:
               1.4987434 = boost
               8.30027 = idf(docFreq=29, maxDocs=44421)
               0.013705967 = queryNorm
             0.91705894 = fieldWeight in 1357, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.30027 = idf(docFreq=29, maxDocs=44421)
               0.078125 = fieldNorm(doc=1357)
       0.16 = coord(4/25)