TGMs capture common behaviour of a society reflected in its training data and throw back those in its output, there are different types of bias that can be apprehended by a TGM ,bias can be
Gender bias ((e.g., favoring males over females)
racial bias (e.g., favoring white over black people)
religious bias (e.g., favoring Christians over Muslims). 


Bias of TGMs

TGMs are used to create task oriented systems 
 - question answering, 
 - reading comprehension, 
 - natural language inference, 
 - machine translation


Beneficial usage of TGMs

 - Fake news generation
 - Fake product review generation
 - spamming/phishing


Malicious Usage of TGMs

 - Bias
 - Beneficial usage
 - Malicious usage


San Jose State University

Machine learning models that can generate text  have attained human level of perfection in the areas of grammar, world knowledge, coherence and fluency.

Automatic Detection of Machine Generated Text

Automatic Detection of Machine Generated Text: A Critical Survey
by Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan
https://arxiv.org/pdf/2011.01314.pdf

Automatic Detection of Machine Generated Text: A Critical Survey


 - Story generation 
 - Conversational response generation
 - Code auto-completion
 - Radiology report generation


Uses of Text Generative Models(TGMs)

 - Fake news generation 
 - Fake product reviews generation 
 - Spamming and phishing


Misuse of Text Generative Models(TGMs)

 - accurate
 - data-efficient
 - generalizable
 - interpretable
 - robust

Qualities of an ideal TGM detector

Most of the latest TGM’s used Transformer model architecture ,it helps to learn long range dependency information and the generated texts are correct ,coherent and uses world knowledge.

Text Generative Model Architecture

It is possible to control the topic and sentiment of text generated ,two methods by which we can control the text generated are

 - Training with control tokens
 - Control using attribute classifier


Controllable Text Generative Models

Detectors are used to identify machine generated text from human generated text. Classification of detectors are based on

- Classifiers trained from scratch 
 - Zero-shot classifier 
 - Fine-tuning NLM 
 - Human-machine collaboration


TGM Classifiers or Detectors

A system that leverages the use of human visual skills and common sense.

- Differences in human and machine detector
 - Supporting untrained humans
 - Real or Fake Text (RoFT) tool     


Human-machine collaboration for TGMs

A Text Generative Model (TGM) is a neural language model that estimates the probability distribution of tokens. It learns parameters $$\theta$$ by minimizing the following negative log-likelihood objective function over a dataset $$\mathcal{D}$$:

$$ \mathcal{L}(p_{\theta}, \mathcal{D}) = - \sum_{j=1}^{|\mathcal{D}|} \sum_{t=1}^{|\textbf{x}^{(j)}|} \log p_{\theta}(x_t^{(j)} \mid x_1^{(j)}, \dots, x_{t-1}^{(j)}) $$

Where:
- $$x_i \in \mathcal{V}$$ is a token from the vocabulary of words.
- $$\textbf{x} = (x_1, \dots, x_{|\textbf{x}|})$$ is a text sequence.
- $$p_*(\textbf{x})$$ is the reference distribution.
- $$\mathcal{D}$$ is a finite set of text sequences drawn from $$p_*$$.
- $$p_{\theta}(x_t \mid x_1, \dots, x_{t-1})$$ is the model's predicted probability of the next token given the previous tokens in the sequence.

Learn Before

Related

Learn After