SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.02453 · 2023

FineDeb: A Debiasing Framework for Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with contextual debiasing of embeddings learned by pretrained language models. The model is then fine-tuned on a language modeling objective. Our results show that FineDeb offers stronger debiasing in comparison to other methods which often result in models as biased as the original language model. Our framework is generalizable for demographics with multiple classes, and we demonstrate its effectiveness through extensive experiments and comparisons with state of the art techniques. We release our code and data on GitHub.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.02453")
get_code_for_paper("2302.02453")
have("2302.02453")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.02453.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.02453.svg)](https://syntology.ai/paper/2302.02453)

Connect an agent — have() is free.