lecture 7 Flashcards

1
Q

GPT-3

A

deep language model
 Question answering, text summarization, classification, etc.

 Controversial when announced
o Might have been too dangerous for the public bc it could be used as manipulation campaigns

 Core idea:
Instructing the model with prompts
 i.e., conditioning its probability function
= what to predict as a next word

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

transformer models

A

o inside the transformer model there are stacked encoders and decoders

o Have an attention mechanism (and a neural network)

o seq2seq

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

seq2seq

A

you take a sequence as an input and you get a sequence as an output

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

attention mechanism

A

 Tells the model to pay attention to more than just the immediate context of a word. (programma verliest de draad niet)

  • since language isn’t structured like this. Relationships between concepts can be quite wide apart. The attention mechanism helps with this
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Autoregressive text generation

A

predicts the next word

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Before deep language models

A

o Human language explained with interpretable models that combine symbolic elements

o Rule based operations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

GPT-3 approach (deep learning)

A

o Learning from data in the wild
 This is the game changer in language models

o No instruction/supervision, no syntax, no rules.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

temperature

A

How much risk you take

o 0 = deterministic (always gives the same)
 Chooses the most likely answer

o 1 = always gives a different answer

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

moral chain of thought

A
  1. Check rule violation
  2. Reflect on purpose of the rule
  3. Consider utility loss and gain

 You need to give GPT-3 instructions to follow certain steps, so that it ‘thinks’ about the problem step-by-step like humans

 If you use default models without using this chain of thought, they can’t make the same decisions that models make

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Linda problem

A

Conjunction fallacy

o GPT-3 is making the same (wrong) mistakes that humans make on the Linda problem

 Not a stochastic parrot and could pass as a subject

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

GPT-3 personality

A

Resembles female participants
 i.e., High in honesty-humility

Low on emotionality

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

GPT-3 values

A

shows theoretically consistent patterns
 High on universalism, benevolence, self direction, and stimulation
 Low on security, conformity, achievement, and power

 i.e., pattern of consistency is the same as in humans
* however, with increased temperature pushes the model to the extremes, goes from female to male, and becomes younger.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

cognitive reflection test

A

elicits intuitive answers that are incorrect
o for this reason, GPT-3 makes the same mistakes that humans make

 this is because it predicts what the most likely answer is. If people are more likely to make mistakes on these questions, so will GPT-3.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Illusory truth effect

A

repetition of information increases subjective truth judgements.
o Regardless of veracity, plausibility, or knowledge of the information

 This also happens with GPT-3 when repeatedly exposed to information.
o Increased exposure increases its truth-rating
o This way, you can intervene with the system’s dynamics

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

emergent abilities

A

An ability is emergent if it is not present in smaller language models, but is present in larger language models
o When quantitative changes in the system results in qualitative changes

 Developing abilities that you didn’t have before bc of phase transitions
 Sudden understanding of a problem when training examples increase

 Quant: model becomes bigger, human becomes older
 Qual: abilities

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

core principles GPT-3 and humans

A
  1. Continuous context-dependent next-word prediction before word onset
  2. Matching pre-onset predictions to the incoming word to induce post-onset surprise
  3. Representing words using contextual embeddings
    a. 3 words that have different meanings in different contexts are interpreted differently
17
Q

Gpt-3 struggles on tasks that

A

o Assess social commonsense and emotional intelligence in social interactions

o Measure its ability to understand other people’s mental states and realities in short stories

because GPT-3 has no ToM