Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements
The growing capability and availability of generative language models has enabled a wide range of new downstream tasks. Academic research has identified, quantified and mitigated biases present in language models but is rarely tailored to downstream tasks where wider impact on individuals and society can be felt. In this work, we leverage one popular generative language model, GPT-3, with the goal of writing unbiased and realistic job advertisements. We first assess the bias and realism of zero-shot generated advertisements and compare them to real-world advertisements. We then evaluate prompt-engineering and fine-tuning as debiasing methods. We find that prompt-engineering with diversity-encouraging prompts gives no significant improvement to bias, nor realism. Conversely, fine-tuning, especially on unbiased real advertisements, can improve realism and reduce bias.
Code (1)
Tasks
DiversityLanguage ModelingLanguage ModellingPrompt EngineeringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods
We introduce a new benchmark, WinoBias, for coreference resolution focused on gender bias. Our corpus contains Winograd-schema style sentences with entities corresponding to people referred by their occupation (e.g. the …
coreference-resolutionCoreference ResolutionData AugmentationDomain and Function: A Dual-Space Model of Semantic Relations and Compositions
Given appropriate representations of the semantic relations between carpenter and wood and between mason and stone (for example, vectors in a vector space model), a suitable algorithm should be able to recognize that the…
Semantic CompositionFabrication-Aware Reverse Engineering for Carpentry
We propose a novel method to generate fabrication blueprints from images of carpentered items. While 3D reconstruction from images is a well-studied problem, typical approaches produce representations that are ill-suited…
3D ReconstructionvalidThinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models
Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions, so they are inaccessible to end-users looking to adapt LLM outputs for their particular need…
Text GenerationUSD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations
Large-scale homepage recommendations face critical challenges from pseudo-negative samples caused by exposure bias, where non-clicks may indicate inattention rather than disinterest. Existing work lacks thorough analysis…
Marketing