A Disability Lens towards Biases in GPT-3 Generated Open-Ended Languages
Not on the map. Why?
Abstract (arXiv)
Language models (LM) are becoming prevalent in many language-based application spaces globally. Although these LMs are improving our day-to-day interactions with digital products, concerns remain whether open-ended languages or text generated from these models reveal any biases toward a specific group of people, thereby risking the usability of a certain product. There is a need to identify whether these models possess bias to improve the fairness in these models. This gap motivates our ongoing work, where we measured the two aspects of bias in GPT-3 generated text through a disability lens.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 9 of its 17 references that are in the map. First posted on arXiv 23 Jun 2022.
Builds on
9 of 17 references.
References · 9
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
- 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
- 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410
- 2022Long Document Summarization with Top-down and Bottom-up Inferencecited by 42
- 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 2.
3 papers.