paper-with-me

홈 › Papers

Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements

2022-05-23 · NAACL (GeBNLP) 2022 7 · Conrad Borchers, Dalia Sara Gala, Benjamin Gilburt, Eduard Oravkin, Wilfried Bounsi, Yuki M. Asano, Hannah Rose Kirk

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.

📄 PDF Abstract BibTeX arXiv:2205.11374

Code (1)

oxai/gpt3-jobadvert-bias 공식 구현

Tasks

DiversityLanguage ModelingLanguage ModellingPrompt Engineering

Methods 이 논문이 사용한 방법론

15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…

Similar Papers 제목 키워드 기반

Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods

2018-04-18 · NAACL 2018 6 · Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez 외

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 Augmentation

Domain and Function: A Dual-Space Model of Semantic Relations and Compositions

2013-09-16 · Peter D. Turney

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 Composition

Fabrication-Aware Reverse Engineering for Carpentry

2021-07-21 · James Noeckel, Haisen Zhao, Brian Curless, Adriana Schulz

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 Reconstructionvalid

Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models

2024-05-16 · Shaz Furniturewala, Surgan Jandial, Abhinav Java, Pragyan Banerjee 외

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 Generation

USD: A User-Intent-Driven Sampling and Dual-Debiasing Framework for Large-Scale Homepage Recommendations

2025-07-09 · Jiaqi Zheng, Cheng Guo, Yi Cao, Chaoqun Hou 외

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