SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.06303 · NAACL · 2022

Using Natural Sentences for Understanding Biases in Language Models

Yi Sun, Sarah Alnegheimish, Alicia Guo

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

Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need of prompt-style dataset to trigger specific behaviors of language models. In this paper, we address this gap by creating a prompt dataset with respect to occupations collected from real-world natural sentences present in Wikipedia. We aim to understand the differences between using template-based prompts and natural sentence prompts when studying gender-occupation biases in language models. We find bias evaluations are very sensitive to the design choices of template prompts, and we propose using natural sentence prompts for systematic evaluations to step away from design choices that could introduce bias in the observations. .

For agents

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

get_harvested_code_for_paper("2205.06303")
get_code_for_paper("2205.06303")
have("2205.06303")

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

curl https://syntology.ai/api/ran/2205.06303.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.06303.svg)](https://syntology.ai/paper/2205.06303)

Connect an agent — have() is free.