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) 0.23

   0.23056439 = sum of:
     0.23056439 = product of:
       1.1528219 = sum of:
         0.009413272 = weight(abstract_txt:which in 873) [ClassicSimilarity], result of:
           0.009413272 = score(doc=873,freq=1.0), product of:
             0.041310135 = queryWeight, product of:
               1.052983 = boost
               2.9167147 = idf(docFreq=6503, maxDocs=44218)
               0.013450588 = queryNorm
             0.22786833 = fieldWeight in 873, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.9167147 = idf(docFreq=6503, maxDocs=44218)
               0.078125 = fieldNorm(doc=873)
         0.088805705 = weight(abstract_txt:requests in 873) [ClassicSimilarity], result of:
           0.088805705 = score(doc=873,freq=2.0), product of:
             0.11619037 = queryWeight, product of:
               1.2487144 = boost
               6.9177637 = idf(docFreq=118, maxDocs=44218)
               0.013450588 = queryNorm
             0.76431215 = fieldWeight in 873, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.9177637 = idf(docFreq=118, maxDocs=44218)
               0.078125 = fieldNorm(doc=873)
         0.024029627 = weight(abstract_txt:model in 873) [ClassicSimilarity], result of:
           0.024029627 = score(doc=873,freq=1.0), product of:
             0.07716036 = queryWeight, product of:
               1.4390974 = boost
               3.986234 = idf(docFreq=2231, maxDocs=44218)
               0.013450588 = queryNorm
             0.31142452 = fieldWeight in 873, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.986234 = idf(docFreq=2231, maxDocs=44218)
               0.078125 = fieldNorm(doc=873)
         0.13361986 = weight(abstract_txt:trained in 873) [ClassicSimilarity], result of:
           0.13361986 = score(doc=873,freq=1.0), product of:
             0.24218293 = queryWeight, product of:
               2.5495577 = boost
               7.062158 = idf(docFreq=102, maxDocs=44218)
               0.013450588 = queryNorm
             0.5517311 = fieldWeight in 873, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.062158 = idf(docFreq=102, maxDocs=44218)
               0.078125 = fieldNorm(doc=873)
         0.89695346 = weight(abstract_txt:chatgpt in 873) [ClassicSimilarity], result of:
           0.89695346 = score(doc=873,freq=5.0), product of:
             0.634984 = queryWeight, product of:
               5.838341 = boost
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.013450588 = queryNorm
             1.4125607 = fieldWeight in 873, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.078125 = fieldNorm(doc=873)
       0.2 = coord(5/25)
   

2. Aydin, Ö.; Karaarslan, E.: OpenAI ChatGPT generated literature review: : digital twin in healthcare (2022) 0.22

   0.2210743 = sum of:
     0.2210743 = product of:
       1.1053715 = sum of:
         0.007987427 = weight(abstract_txt:which in 851) [ClassicSimilarity], result of:
           0.007987427 = score(doc=851,freq=2.0), product of:
             0.041310135 = queryWeight, product of:
               1.052983 = boost
               2.9167147 = idf(docFreq=6503, maxDocs=44218)
               0.013450588 = queryNorm
             0.1933527 = fieldWeight in 851, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.9167147 = idf(docFreq=6503, maxDocs=44218)
               0.046875 = fieldNorm(doc=851)
         0.024972323 = weight(abstract_txt:model in 851) [ClassicSimilarity], result of:
           0.024972323 = score(doc=851,freq=3.0), product of:
             0.07716036 = queryWeight, product of:
               1.4390974 = boost
               3.986234 = idf(docFreq=2231, maxDocs=44218)
               0.013450588 = queryNorm
             0.32364187 = fieldWeight in 851, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.986234 = idf(docFreq=2231, maxDocs=44218)
               0.046875 = fieldNorm(doc=851)
         0.065773524 = weight(abstract_txt:conversational in 851) [ClassicSimilarity], result of:
           0.065773524 = score(doc=851,freq=1.0), product of:
             0.16845585 = queryWeight, product of:
               1.5035613 = boost
               8.329592 = idf(docFreq=28, maxDocs=44218)
               0.013450588 = queryNorm
             0.3904496 = fieldWeight in 851, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.329592 = idf(docFreq=28, maxDocs=44218)
               0.046875 = fieldNorm(doc=851)
         0.13886182 = weight(abstract_txt:trained in 851) [ClassicSimilarity], result of:
           0.13886182 = score(doc=851,freq=3.0), product of:
             0.24218293 = queryWeight, product of:
               2.5495577 = boost
               7.062158 = idf(docFreq=102, maxDocs=44218)
               0.013450588 = queryNorm
             0.57337576 = fieldWeight in 851, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.062158 = idf(docFreq=102, maxDocs=44218)
               0.046875 = fieldNorm(doc=851)
         0.8677764 = weight(abstract_txt:chatgpt in 851) [ClassicSimilarity], result of:
           0.8677764 = score(doc=851,freq=13.0), product of:
             0.634984 = queryWeight, product of:
               5.838341 = boost
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.013450588 = queryNorm
             1.3666114 = fieldWeight in 851, product of:
               3.6055512 = tf(freq=13.0), with freq of:
                 13.0 = termFreq=13.0
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.046875 = fieldNorm(doc=851)
       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) 0.21

   0.20642348 = sum of:
     0.20642348 = product of:
       1.0321174 = sum of:
         0.009413272 = weight(abstract_txt:which in 943) [ClassicSimilarity], result of:
           0.009413272 = score(doc=943,freq=1.0), product of:
             0.041310135 = queryWeight, product of:
               1.052983 = boost
               2.9167147 = idf(docFreq=6503, maxDocs=44218)
               0.013450588 = queryNorm
             0.22786833 = fieldWeight in 943, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.9167147 = idf(docFreq=6503, maxDocs=44218)
               0.078125 = fieldNorm(doc=943)
         0.06279512 = weight(abstract_txt:requests in 943) [ClassicSimilarity], result of:
           0.06279512 = score(doc=943,freq=1.0), product of:
             0.11619037 = queryWeight, product of:
               1.2487144 = boost
               6.9177637 = idf(docFreq=118, maxDocs=44218)
               0.013450588 = queryNorm
             0.5404503 = fieldWeight in 943, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.9177637 = idf(docFreq=118, maxDocs=44218)
               0.078125 = fieldNorm(doc=943)
         0.024029627 = weight(abstract_txt:model in 943) [ClassicSimilarity], result of:
           0.024029627 = score(doc=943,freq=1.0), product of:
             0.07716036 = queryWeight, product of:
               1.4390974 = boost
               3.986234 = idf(docFreq=2231, maxDocs=44218)
               0.013450588 = queryNorm
             0.31142452 = fieldWeight in 943, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.986234 = idf(docFreq=2231, maxDocs=44218)
               0.078125 = fieldNorm(doc=943)
         0.13361986 = weight(abstract_txt:trained in 943) [ClassicSimilarity], result of:
           0.13361986 = score(doc=943,freq=1.0), product of:
             0.24218293 = queryWeight, product of:
               2.5495577 = boost
               7.062158 = idf(docFreq=102, maxDocs=44218)
               0.013450588 = queryNorm
             0.5517311 = fieldWeight in 943, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.062158 = idf(docFreq=102, maxDocs=44218)
               0.078125 = fieldNorm(doc=943)
         0.8022595 = weight(abstract_txt:chatgpt in 943) [ClassicSimilarity], result of:
           0.8022595 = score(doc=943,freq=4.0), product of:
             0.634984 = queryWeight, product of:
               5.838341 = boost
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.013450588 = queryNorm
             1.2634326 = fieldWeight in 943, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.078125 = fieldNorm(doc=943)
       0.2 = coord(5/25)
   

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

   0.102689214 = sum of:
     0.102689214 = product of:
       2.5672305 = sum of:
         2.5672305 = weight(abstract_txt:chatgpt in 848) [ClassicSimilarity], result of:
           2.5672305 = score(doc=848,freq=1.0), product of:
             0.634984 = queryWeight, product of:
               5.838341 = boost
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.013450588 = queryNorm
             4.0429845 = fieldWeight in 848, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.085969 = idf(docFreq=36, maxDocs=44218)
               0.5 = fieldNorm(doc=848)
       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

   0.08103365 = sum of:
     0.08103365 = product of:
       0.5064603 = sum of:
         0.0388534 = weight(abstract_txt:response in 356) [ClassicSimilarity], result of:
           0.0388534 = score(doc=356,freq=1.0), product of:
             0.084366925 = queryWeight, product of:
               1.0640553 = boost
               5.8947687 = idf(docFreq=330, maxDocs=44218)
               0.013450588 = queryNorm
             0.4605288 = fieldWeight in 356, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.8947687 = idf(docFreq=330, maxDocs=44218)
               0.078125 = fieldNorm(doc=356)
         0.17732173 = weight(abstract_txt:dialogue in 356) [ClassicSimilarity], result of:
           0.17732173 = score(doc=356,freq=5.0), product of:
             0.13574928 = queryWeight, product of:
               1.3497298 = boost
               7.4773793 = idf(docFreq=67, maxDocs=44218)
               0.013450588 = queryNorm
             1.3062444 = fieldWeight in 356, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.4773793 = idf(docFreq=67, maxDocs=44218)
               0.078125 = fieldNorm(doc=356)
         0.13525547 = weight(abstract_txt:inappropriate in 356) [ClassicSimilarity], result of:
           0.13525547 = score(doc=356,freq=2.0), product of:
             0.15380818 = queryWeight, product of:
               1.4367056 = boost
               7.9592175 = idf(docFreq=41, maxDocs=44218)
               0.013450588 = queryNorm
             0.8793776 = fieldWeight in 356, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               7.9592175 = idf(docFreq=41, maxDocs=44218)
               0.078125 = fieldNorm(doc=356)
         0.15502968 = weight(abstract_txt:conversational in 356) [ClassicSimilarity], result of:
           0.15502968 = score(doc=356,freq=2.0), product of:
             0.16845585 = queryWeight, product of:
               1.5035613 = boost
               8.329592 = idf(docFreq=28, maxDocs=44218)
               0.013450588 = queryNorm
             0.9202986 = fieldWeight in 356, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.329592 = idf(docFreq=28, maxDocs=44218)
               0.078125 = fieldNorm(doc=356)
       0.16 = coord(4/25)