Artificial Intelligence Stack Exchange

2 votes

1 answer

459 views

Can we use a pre trained Encoder (BERT, XLM ) with a Decoder (GPT, Transformer-XL) to build a Chatbot instead of Language Translation?

CommunityBot

1

modified 22 hours ago

0 votes

0 answers

25 views

Creating or using a corpus for a chatbot interaction modelling for an existing intelligent tutor system

kokumajutsu

31

modified yesterday

0 votes

0 answers

21 views

Can I reduce computation by only predicting response tokens in a transformer and still get the same gradients?

Tianchen Zheng

1

asked 2 days ago

0 votes

0 answers

25 views

How does a LLM (specifically transformer) pick words from it's vocabulary?

MLBeginner

1

asked 2 days ago

2 votes

2 answers

55 views

Are any AI systems available, or in development, for finding and analysing fallacious inference in natural language text?

Volker Siegel

272

modified 2 days ago

1 vote

1 answer

98 views

How would the probability of a document $P(d)$ be computed in the Naive Bayes classifier?

CommunityBot

1

modified 2 days ago

0 votes

1 answer

34 views

If we prompt a large language model on a task, will its ability for other tasks be affected? How to recover?

Volker Siegel

272

modified Mar 26 at 11:18

1 vote

1 answer

252 views

How can I identify bigrams and trigrams that represent concepts?

CommunityBot

1

modified Mar 25 at 19:00

13 votes

6 answers

491 views

Have any AI systems yet been developed that can knowingly lie to / deceive a human?

Volker Siegel

272

answered Mar 24 at 10:36

1 vote

4 answers

143 views

Could we code in Natural language once we pass the Turing test?

Jaume Oliver Lafont

708

modified Mar 24 at 10:34

1 vote

1 answer

63 views

SparseGPT code reproduction

user68072

33

answered Mar 24 at 3:52

2 votes

1 answer

217 views

How can I build an AI with NLP that reads and understands documents?

Liam Dawson

1

modified Mar 21 at 20:09

1 vote

1 answer

53 views

Large Language Models vs Tabular Data

Ggjj11

149

answered Mar 19 at 11:05

0 votes

0 answers

8 views

How are the softmax normalized weights in ELMo actually learned and computed?

Propr

1

asked Mar 19 at 0:59

Stack Exchange Network

Explore our questions

Can we use a pre trained Encoder (BERT, XLM ) with a Decoder (GPT, Transformer-XL) to build a Chatbot instead of Language Translation?

Creating or using a corpus for a chatbot interaction modelling for an existing intelligent tutor system

Can I reduce computation by only predicting response tokens in a transformer and still get the same gradients?

How does a LLM (specifically transformer) pick words from it's vocabulary?

Are any AI systems available, or in development, for finding and analysing fallacious inference in natural language text?

How would the probability of a document $P(d)$ be computed in the Naive Bayes classifier?

If we prompt a large language model on a task, will its ability for other tasks be affected? How to recover?

How can I identify bigrams and trigrams that represent concepts?

Have any AI systems yet been developed that can knowingly lie to / deceive a human?

Could we code in Natural language once we pass the Turing test?

SparseGPT code reproduction

How can I build an AI with NLP that reads and understands documents?

Large Language Models vs Tabular Data

How are the softmax normalized weights in ELMo actually learned and computed?

Hot Network Questions