Bischoff, M.: Wie eine KI lernt, sich selbst zu erklären (2023)
0.03
0.029464992 = product of:
0.06875165 = sum of:
0.028074749 = weight(_text_:und in 956) [ClassicSimilarity], result of:
0.028074749 = score(doc=956,freq=4.0), product of:
0.1013361 = queryWeight, product of:
2.216367 = idf(docFreq=13101, maxDocs=44218)
0.045721713 = queryNorm
0.27704588 = fieldWeight in 956, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
2.216367 = idf(docFreq=13101, maxDocs=44218)
0.0625 = fieldNorm(doc=956)
0.0074775247 = weight(_text_:in in 956) [ClassicSimilarity], result of:
0.0074775247 = score(doc=956,freq=2.0), product of:
0.062193166 = queryWeight, product of:
1.3602545 = idf(docFreq=30841, maxDocs=44218)
0.045721713 = queryNorm
0.120230645 = fieldWeight in 956, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
1.3602545 = idf(docFreq=30841, maxDocs=44218)
0.0625 = fieldNorm(doc=956)
0.033199377 = weight(_text_:den in 956) [ClassicSimilarity], result of:
0.033199377 = score(doc=956,freq=2.0), product of:
0.13104749 = queryWeight, product of:
2.866198 = idf(docFreq=6840, maxDocs=44218)
0.045721713 = queryNorm
0.25333852 = fieldWeight in 956, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
2.866198 = idf(docFreq=6840, maxDocs=44218)
0.0625 = fieldNorm(doc=956)
0.42857143 = coord(3/7)
- Abstract
- Große Sprachmodelle wie ChatGPT und Co. neigen dazu, Dinge zu erfinden. Durch einen neuen Ansatz können die Systeme ihre Antworten nun erklären - zumindest teilweise. Vorstellung von Modulen (Luminous, AtMan), die die Zusammenstellung der Aussagen in den Antworten analysieren und erklären.
