Detecting Hate Speech with GPT-3

Chiu, Ke-Li; Collins, Annie; Alexander, Rohan

doi:10.48550/arxiv.2103.12407

“…Debouche have also raised similar concerns for the utilization of GPT-3 and recommended authors to openly share the prompts and outcomes used [5]. Other issues include embedded biases (such as hate speech towards race, sexism) [3,11], exploitation of workers for data labeling, permissions on the data used for training and environmental concerns due to the energy used in algorithm training [16].…”

Section: Gpt-3 In Academic Writingmentioning

confidence: 99%

Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency

Buruk¹

2023

Preprint

View full text Add to dashboard Cite

The debate around the use of GPT-3.5 has been a popular topic among academics since the release of ChatGPT. Whilst some have argued for the advantages of GPT-3.5 in enhancing academic writing, others have raised concerns such as plagiarism, the spread of false information, and ecological issues. The need for finding ways to use GPT-3.5 models transparently has been voiced, and suggestions have been made on social media as to how to use GPT-3.5 models in a smart way. Nevertheless, to date, there is a lack of literature which clearly outlines how to use GPT-3.5 models in academic writing, how effective they are, and how to use them transparently. To address this, I conducted a personal experience experiment with GPT-3.5, specifically by using text-davinci-003 model of OpenAI, for writing this article. I identified five ways of using GPT-3.5: Chunk Stylist, Bullet-to-Paragraph, Talk Textualizer, Research Buddy, and Polisher. I reflected on their efficacy, and commented on their potential impact on writing ethics. Additionally, I provided a comprehensive document which shows the prompts I used, results I got from GPT-3.5, the final edits and visually compares those by showing the differences in percentage.

show abstract

“…Debouche have also raised similar concerns for the utilization of GPT-3 and recommended authors to openly share the prompts and outcomes used [5]. Other issues include embedded biases (such as hate speech towards race, sexism) [3,11], exploitation of workers for data labeling, permissions on the data used for training and environmental concerns due to the energy used in algorithm training [16].…”

Section: Gpt-3 In Academic Writingmentioning

confidence: 99%

Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency

Buruk¹

2023

Preprint

0

View full text Add to dashboard Cite

The debate around the use of GPT-3.5 has been a popular topic among academics since the release of ChatGPT. Whilst some have argued for the advantages of GPT-3.5 in enhancing academic writing, others have raised concerns such as plagiarism, the spread of false information, and ecological issues. The need for finding ways to use GPT-3.5 models transparently has been voiced, and suggestions have been made on social media as to how to use GPT-3.5 models in a smart way. Nevertheless, to date, there is a lack of literature which clearly outlines how to use GPT-3.5 models in academic writing, how effective they are, and how to use them transparently. To address this, I conducted a personal experience experiment with GPT-3.5, specifically by using text-davinci-003 model of OpenAI, for writing this article. I identified five ways of using GPT-3.5: Chunk Stylist, Bullet-to-Paragraph, Talk Textualizer, Research Buddy, and Polisher. I reflected on their efficacy, and commented on their potential impact on writing ethics. Additionally, I provided a comprehensive document which shows the prompts I used, results I got from GPT-3.5, the final edits and visually compares those by showing the differences in percentage.

show abstract

“…Classification (6) hate speech detection [24], tweet-classifier, esrb rating, Automatically generating Request for Admissions, evaluate quiz answers, Classify news topics (AI21)…”

Section: A Identifying Llm Primitive Operations Primitive Online Demosmentioning

confidence: 99%

AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts

Wu¹,

Terry²,

Cai³

2021

Preprint

View full text Add to dashboard Cite

Although large language models (LLMs) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, we introduce the concept of Chaining LLM steps together, where the output of one step becomes the input for the next, thus aggregating the gains per step. We first define a set of LLM primitive operations useful for Chain construction, then present an interactive system where users can modify these Chains, along with their intermediate results, in a modular way. In a 20-person user study, we found that Chaining not only improved the quality of task outcomes, but also significantly enhanced system transparency, controllability, and sense of collaboration. Additionally, we saw that users developed new ways of interacting with LLMs through Chains: they leveraged sub-tasks to calibrate model expectations, compared and contrasted alternative strategies by observing parallel downstream effects, and debugged unexpected model outputs by "unit-testing" sub-components of a Chain. In two case studies, we further explore how LLM Chains may be used in future applications.

show abstract

Detecting Hate Speech with GPT-3

Cited by 22 publications

References 11 publications

Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency

Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency

Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency

AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts

Contact Info

Product

Resources

About